“I am pleased to be able to recognize all of this hard work,” said Dean Vivek Sarkar during the ceremony.

One student, two staff members, and four faculty members were nominated by their SCP peers and received awards for their achievements over the past year. 

Student Solves Real World Problems

Yibin Yang (Ph.D. CS 2025) was awarded a 2025 Dissertation Award for his thesis on zero-knowledge proofs in real-world problems. SCP Professor and Senior Associate Chair Vlad Kolesnikov advised Yang and acknowledged that Yang’s work advances the field of cryptography. 

Yang contributed to the advancement of zero-knowledge proofs and multi-party computations, while also building toolchains that are faster and more usable than existing systems. His work earned a distinguished paper award at the 2023 ACM CCS, and he also served as an RSAC Security Scholar.

Staff Lead the Way

In the staff category, Mary Helen Hayes was awarded the Outstanding Staff Leadership Award, and Gina Anderson received the Ruthie Book Outstanding Staff Team Member Award.

The Outstanding Staff Leadership Award is given to a full-time administrative staff member in recognition of an outstanding record of leadership that has resulted in a significant positive impact on the College of Computing, the Institute, or the computing community. Hayes was nominated by four faculty and staff members for this award for her steady presence in SCP since she began her role as director of research operations in 2024. 

The Ruthie Book Outstanding Staff Team Member Award is presented to a staff member in recognition of their outstanding performance in honor of Ruthie Book, who exemplified excellence in her work. Anderson was nominated by SCP faculty and staff for her outstanding leadership and mentorship as assistant director of business operations.

Both received praise for their hard work from the college as well as from their supervisor, Senior Academic Officer Jan Morian. 

“I am so incredibly proud of our staff in the School of Cybersecurity and Privacy who won awards this year at the College of Computing Annual Awards ceremony,” she said.

“Mary Helen Hayes and Regina Anderson are truly outstanding staff members who exemplify Georgia Tech’s values. Their leadership has contributed substantially to the success of the school.”

Cybersecurity Faculty Net Four Awards

The College of Computing also recognized four SCP faculty members for excellence in teaching and research during the college’s annual award ceremony. 

Assistant Professor Teodora Baluta received the Junior Faculty Teaching Award for developing a new graduate-level course that brought together generative artificial intelligence (AI) security, adversarial machine learning, cryptography, and differential privacy. Her nominator, SCP Associate Professor Vassilis Zikas, said the course bridged a critical gap in a rapidly evolving area of computing. 

For his role in leading Team Atlanta to victory in the DARPA AI Cyber Challenge, Professor Taesoo Kim received the Outstanding Senior Faculty Research Award. His nominator, Regents Professor Wenke Lee, praised the team’s performance, which not only won the competition but also beat the combined score of all other competitors. The AI developed by Team Atlanta is now open sourced with the Open Source Security Foundation. 

Associate Professor Frank Li received the Junior Faculty Research Award for establishing world-class research BEES Lab at Georgia Tech. One of his nominators, Associate Professor Saman Zonouz, put Li’s name forward for his work empirically evaluating and improving internet security and privacy from an operational standpoint. 

Finally, Associate Professor Brendan Saltaformaggio received the Mid-Career Faculty Research Award. Zikas nominated him for establishing internationally recognized research in cybersecurity forensics, malware analysis, AI security, and software supply chain security. Saltaformaggio’s research highlights include the discovery of over $2 billion in stolen funds on the Ethereum blockchain. 

"We know SCP faculty conduct highly impactful research that is of the highest quality,” said SCP Interim Chair Mustaque Ahamad. “Our faculty receiving research awards at all levels recognizes this and shows how we are working to realize SCP’s vision of creating security for everyone and everything."

The College recognized outstanding achievements across faculty, staff, and students during the 35th Annual College of Computing Awards celebration, held on April 20 in the Klaus Atrium. Hosted by Dean Vivek Sarkar, the luncheon highlighted significant contributions to the College community, with several honorees from the School of Computing Instruction (SCI). 

Now, the team is working with the Linux Foundation and the Open Source Security Foundation (OpenSSF) to ensure that its breakthrough doesn’t remain confined to a competition environment. The team’s new initiative, OSS-CRS, aims to standardize and operationalize cyber reasoning systems (CRSs) for real-world use.

“The AI Cyber Challenge pushed the boundaries of autonomous software security, with seven teams developing systems capable of finding and remediating vulnerabilities at scale,” said Andrew Chin, a Georgia Tech Ph.D. student and lead on the OSS-CRS program. 

“However, after the competition’s conclusion, it has been difficult to apply these advancements to the open-source community due to infrastructure incompatibilities and the lack of long-term maintenance for the open-sourced CRS implementations.”

To address this gap, Georgia Tech’s Systems Software Lab (SSLab), directed by Professor Taesoo Kim, is leading the development of OSS-CRS, which provides both a common framework for CRS development and the infrastructure needed to deploy these systems seamlessly across open-source projects.

As part of this effort, the team has ported its competition-winning system, Atlantis, into the OSS-CRS framework. The move makes it compatible with laptops and other everyday machines with flexible resource and budget configurations.

Interoperability is also central to the framework’s design. Atlantis can be combined with other CRSs to improve performance, including systems developed by fellow AIxCC finalists and newer agentic, command-line-based tools. This modular approach reflects a key lesson the team learned from the competition: collaboration between systems can outperform any single solution.

OSS-CRS has been accepted as a sandbox project within OpenSSF’s AI/ML Security Working Group, a milestone that brings added technical guidance and community support to the project. This includes:

• Access to mentorship
• Dedicated working group meetings
• Broader visibility through industry events, publications, and outreach efforts

The collaboration will also foster stronger connections with open-source maintainers, helping streamline vulnerability disclosure and remediation workflows.

They would normally get this in their natural habitats while foraging for food and staying alert to predators that might target calves.

However, the four elephants reside at Zoo Atlanta, so they don’t have to worry about these things.

That’s why zoo caretakers are always on the lookout for better ways to help their elephants exercise their brains.

The caretakers at Zoo Atlanta found one when they met Arianna Mastali, a Ph.D. student in Georgia Tech’s School of Interactive Computing. Mastali designed an audio enrichment wall to help stimulate Zoo Atlanta’s elephants.

Many zoos build concrete enrichment walls to foster elephant problem-solving and critical thinking. The walls usually have holes for the elephants to reach through with their trunks as they search for food, treats, or playful objects on the other side.

Mastali enhanced Zoo Atlanta’s enrichment wall by adding an interactive audio component. A nearby speaker system emits distinctive low-frequency tones when an elephant sticks its trunk into a hole.

“They’re intelligent creatures that require a lot of complexity in their habitat,” Mastali said. “We wanted to add to that complexity while giving them more control.”

Experimenting in the Wild

Mastali’s system uses cameras and computer vision to detect when an elephant’s trunk is inside a hole and then sends a signal to the speakers to play a sound.

Mastali is a member of the Georgia Tech Animal Lab, directed by School of IC professor Melody Jackson. The lab often uses sensing technology to enhance animal wellness.

Mastali said she tried incorporating sensing devices into her project several times. She constructed an insert made of PVC pipe and attached a sensor to its base that used infrared beams to detect the elephant’s trunk.

However, she said it was difficult to account for the elephants’ strength. Their trunks would break the insert after a day or two. 

She pivoted toward computer vision to remove the risk of damage and keep the enrichment wall as close to natural as possible. 

“A big lesson we learned was that using existing materials the elephants are already familiar with was the best way to do things, and it simplified our design process,” she said.

Shane Rosse, a student in Georgia Tech’s Online Master of Science in Computer Science (OMSCS) program, assisted Mastali with the computer vision component.

Enhancing Environmental Enrichment

Mastali observed the elephants’ behavior at the wall seven days before and seven days after the installation of the audio enrichment system.

The number of times the elephants approached the wall after installation increased by 176%, and time spent at the wall increased by 71%

“We weren’t sure at first if they would care that much, so it was great to see how much time they spent at the wall, especially our less dominant females,” said Kirby Miller, senior elephant caretaker at Zoo Atlanta. “They seem to like it the most.”

Miller said the elephants used to only approach the wall when they knew there was food behind it. That started to change after the audio enrichment system was installed.

“We would be off somewhere else, and we’d hear the speaker playing the sounds, and we knew there wasn’t any food back there,” Miller said. “Tara had her trunk in one of the holes, just listening to the sound. That let us know they do like it, and they’re very curious about it.”

Miller said because elephants have sharp memories and acute senses of hearing and smell, their habitats must be designed with that in mind.

Zoo Atlanta’s African Savanna elephant habitat was redesigned in 2019. In addition to the enrichment wall, it includes a bathing pond, two waterfalls, and swing boom devices that hold hay for elephants to eat as they would in the wild.

Miller said elephants sheltered at any zoo or conservation would benefit from enrichment devices enhanced by technology.

“I think anything they can participate in that gives them choice and control is great for all zoo elephants,” she said. “It depends on the elephants, but with our elephants, they can hear much higher frequencies than we can. That noise isn’t that loud for us, but for them, they’re feeling that noise, and they can hear much more, which makes it more stimulating for them.”

Georgia Tech researchers are making AI easier to understand through their work on Transformer Explainer. The free, online tool shows non-experts how ChatGPT, Claude, and other large language models (LLMs) process language. 

Transformer Explainer is easy to use and runs on any web browser. It quickly went viral after its debut, reaching 150,000 users in its first three months. More than 563,000 people worldwide have used the tool so far.

Global interest in Transformer Explainer continues when the team presents the tool at the 2026 Conference on Human Factors in Computing Systems (CHI 2026). CHI, the world’s most prestigious conference on human-computer interaction, will take place in Barcelona, April 13-17.

[Related: GT @ CHI 2026]

“There are moments when LLMs can seem almost like a person with their own will and personality, and that misperception has real consequences. For example, there have been cases where teenagers have made poor decisions based on conversations with LLMs,” said Ph.D. student Aeree Cho.

“Understanding that an LLM is fundamentally a model that predicts the probability distribution of the next token helps users avoid taking its outputs as absolute. What you put in shapes what comes out, and that understanding helps people engage with AI more carefully and critically.”

A transformer is a neural network architecture that changes data input sequence into an output. Text, audio, and images are forms of processed data, which is why transformers are common in generative AI models. They do this by learning context and tracking mathematical relationships between sequence components.

Transformer Explainer demystifies how transformers work. The platform uses visualization and interaction to show, step by step, how text flows through a model and produces predictions.

Using this approach, Transformer Explainer impacts the AI landscape in four main ways:

• It counters hype and misconceptions surrounding AI by showing how transformers work.
• It improves AI literacy among users by removing technical barriers and lowering the entry for learning about AI.
• It expands AI education by helping instructors teach AI mechanisms without extensive setup or computing resources.
• It influences future development of AI tools and educational techniques by providing a blueprint for interpretable AI systems.

“When I first learned about transformers, I felt overwhelmed. A transformer model has many parts, each with its own complex math. Existing resources typically present all this information at once, making it difficult to see how everything fits together,” said Grace Kim, a dual B.S./M.S. computer science student. 

“By leveraging interactive visualization, we use levels of abstraction to first show the big picture of the entire model. Then users click into individual parts to reveal the underlying details and math. This way, Transformer Explainer makes learning far less intimidating.”

Many users don’t know what transformers are or how they work. The Georgia Tech team found that people often misunderstand AI. Some label AI with human-like characteristics, such as creativity. Others even describe it as working like magic.

Furthermore, barriers make it hard for students interested in transformers to start learning. Tutorials tend to be too technical and overwhelm beginners with math and code. While visualization tools exist, these often target more advanced AI experts.

Transformer Explainer overcomes these obstacles through its interactive, user-focused platform. It runs a familiar GPT model directly in any web browser, requiring no installation or special hardware. 

Users can enter their own text and watch the model predict the next word in real time. Sankey-style diagrams show how information moves through embeddings, attention heads, and transformer blocks.

The platform also lets users switch between high-level concepts and detailed math. By adjusting temperature settings, users can see how randomness affects predictions. This reveals how probabilities drive AI outputs, rather than creativity.

“Millions of people around the world interact with transformer-driven AI. We believe that it is crucial to bridge the gap between day-to-day user experience and the models' technical reality, ensuring these tools are not misinterpreted as human-like or seen as sentient,” said Ph.D. student Alex Karpekov. 

“Explaining the architecture helps users recognize that language generated by models is a product of computation, leading to a more grounded engagement with the technology.” 

Cho, Karpekov, and Kim led the development of Transformer Explainer. Ph.D. students Alec Helbling, Seongmin Lee, Ben Hoover, and alumni Zijie (Jay) Wang (Ph.D. ML-CSE 2024) and Minsuk Kahng (Ph.D. CS-CSE 2019) assisted on the project. 

Professor Polo Chau supervised the group and their work. His lab focuses on data science, human-centered AI, and visualization for social good.

Acceptance at CHI 2026 stems from the team winning the best poster award at the 2024 IEEE Visualization Conference. This recognition from one of the top venues in visualization research highlights Transformer Explainer’s effectiveness in teaching how transformers work.

“Transformer Explainer has reached over half a million learners worldwide,” said Chau, a faculty member in the School of Computational Science and Engineering. 

“I'm thrilled to see it extend Georgia Tech's mission of expanding access to higher education, now to anyone with a web browser.”

The Iranian regime’s internet shutdown, initiated on Jan. 8, 2026, has severely diminished the flow of information out of the country. Without internet access, little news about the national protests that flared between Dec. 30, 2025, and Jan. 13, 2026, and the regime’s violent crackdown has reached the world. Many digital rights and internet monitoring groups have assessed the current shutdown to be the most sophisticated and most severe in Iran’s history.

We are a social scientist and two computer scientists at the Georgia Institute of Technology’s Internet Intelligence Lab who study internet connectivity.

Through the Internet Outage Detection and Analysis project, we have been measuring internet connectivity globally since 2011. The project was motivated by the internet shutdowns during the Arab Spring mass protests that began in December 2010 against Middle Eastern and North African regimes.

The project provides a public dashboard of internet connectivity measurements. Its long view of global internet connectivity offers insight into the Iranian regime’s developing sophistication in controlling information and shutting down the internet in the country.

Our measurements show that Iran has been in a complete internet shutdown since Jan. 8. This is longer than the 48½-hour shutdown in June 2025 during the Israel-Iran war and surpasses the duration of the November 2019 shutdown that lasted almost seven days. Compared to the two weeks of nightly mobile phone network shutdowns in September to October of 2022 during the Women, Life, Freedom protests, this shutdown is more complete by also closing down fixed-line connectivity.

Measuring Internet Connectivity

The Internet Outage Detection and Analysis project measures global internet connectivity through three signals related to internet infrastructure: routing announcements, active probing and internet background noise.

Core routers, unlike the router in your home, are responsible for directing traffic to and from networks. Routing announcements are how they communicate with each other. If a nation’s network of routers stop making these announcements, the network will disappear from the global internet.

We also measure the responsiveness of networks through probing. To create the probing signal, we continuously ping devices in millions of networks around the globe. Most devices are designed to automatically respond to these pings by echoing them back to the sender. We collect these responses and label networks as “connected/active.”

A tool we use dubbed “network telescope” captures internet background noise – traffic generated by hundreds of thousands of internet hosts worldwide. A drop in this signal can indicate an outage.

A History of Shutdowns

The first nationwide shutdown that the Internet Outage Detection and Analysis project observed in Iran was during the “Bloody November” uprising that happened in 2019. During that shutdown, the primary method the regime used was turning off routing announcements, which stopped all traffic between routers. This is a blunt force tool that makes the internet essentially go dark; no connectivity is possible for affected networks.

However, our measurement reporting showed differences in signal-drop patterns among the three data sources we track. These patterns demonstrate the regime’s adoption of diverse disconnection mechanisms and large differences in the timing of disconnection by various Iranian internet service providers (ISPs).

This reporting also showed evidence that the 2019 blackout was not complete and some people were able to circumvent it. Nevertheless, as documented by Amnesty International, the internet darkness created a “web of impunity” that allowed the regime to violate international human rights law without any accountability.

In September 2022, the Women, Life, Freedom protests erupted after the killing of Mahsa Amini in state custody. To suppress the nationwide mobilization without exacting a high cost, the Iranian regime implemented nightly shutdowns affecting only mobile networks. Keeping fixed-line internet connections online limited the impact of these shutdowns to mitigate the economic, political and social costs.

These nightly internet curfews lasted about two weeks. During this time the regime implemented other forms of censorship, specifically blocking applications to further control the information environment and to prevent access to technologies for circumventing censorship.

In June 2025, the Israel-Iran war began and we observed initial degradation in internet connectivity, which often occurs during times of conflict, when internet and power infrastructure are affected by missile attacks. The Iranian regime shut down the internet over four days, citing national security as its rationale.

That time, the regime did not use routing announcements to implement the shutdown. Our measurement data shows that routing announcements were largely unaffected. Instead, the Iranian regime implemented the shutdown by interfering with key protocols that allow the internet to function, including transport layer security and the domain name system.

The regime used these techniques to shut off Iran’s connectivity with the global internet while allowing specific, sanctioned access in a policy called whitelisting. This strategy shows an increased sophistication in how the Iranian regime implements shutdowns and controls the flow of information.

Organizations that support digital human rights in Iran report that some Iranians were able to circumvent the shutdown using virtual private networks and various censorship-resilient technologies such as peer-to-peer networks.

Jan. 8, 2026

On Dec. 30, 2025, the Internet Outage Detection and Analysis project team received reports of internet disruptions amid the start of nationwide protests. At 8 p.m. Iran Standard Time on Jan. 8, 2026, the Iranian regime shut down the internet. Our measurements show a nominal amount of responsiveness to our active probing, about 3%. This small amount could be an artifact of our measurements or lingering connectivity for whitelisted access, for example for Iranian government officials and services.

Outside of very limited whitelisted connectivity, digital human rights groups reported severely limited access to the internet both internationally and domestically. According to digital rights group Project Ainita, the Iranian regime implemented the shutdown by interfering with transport layer security and the domain name system. In addition, landline phone calls have been only intermittently available.

Aside from these more sophisticated techniques, this shutdown evokes the Bloody November shutdown of 2019 in that it has been ordered during a time of protest with mass civilian casualties.

Jammed Satellites

Since Russia’s full-scale invasion of Ukraine in 2022, low Earth orbit satellite services, such as Starlink, can help people maintain internet connectivity during outages and government-ordered shutdowns. These satellite services can allow users to bypass damaged or state-censored terrestrial internet infrastructure.

However, accessing the internet via satellite services during a shutdown is not without risk. User terminals communicate with satellites via radio frequency links that can be detected through surveillance, for example from planes or drones, potentially exposing users’ locations and putting them at risk of being identified. Currently, the Iranian regime is using jammers to degrade the Starlink connection.

One of the most significant barriers to connecting users in Iran to satellite services is a logistical one. Providing connectivity via Starlink’s service would require distributing a large number of user terminals within the country, a feat that would be difficult because the devices are likely to be considered illegal contraband by the government. This severely limits the scale at which such services can be adopted.

Recent technological developments, however, may partially mitigate this challenge. Starlink’s direct-to-cell capability, which aims to provide LTE cellular connectivity directly to ordinary cellphones, could reduce dependence on specialized hardware. If they become widely available, such systems would allow users to connect using common devices already in circulation, sidestepping one of the most difficult barriers to providing connectivity.

Like other radio-based communications, however, direct-to-cell connectivity would remain vulnerable to signal jamming and other forms of electronic interference by the government.

For the time being, the Iranian regime controls the country’s internet infrastructure, which means it still has a virtual off switch.

This article is republished from The Conversation under a Creative Commons license. Read the original article.

The programming style relies on using generative artificial intelligence (AI) to create software code using tools like Claude, Gemini, and GitHub Copilot. According to graduate research assistant Hanqing Zhao of the Systems Software & Security Lab (SSLab), no one had been tracking these common vulnerabilities and exposures before the launch of their Vibe Security Radar.

“The vulnerabilities we found lead to breaches,” he said. “Everyone is using these tools now. We need a feedback loop to identify which tools, which patterns, and which workflows create the most risk.”

The radar extensively scans public vulnerability databases, finds the error for each vulnerability, and then examines the code’s history to find who introduced the bug. If they discover an AI tool's signature, the radar flags it. 

Of the 74 confirmed cases uncovered so far by the tool, 14 are critical risks, and 25 are high. These vulnerabilities include command injection, authentication bypass, and server-side request forgery. Zhao explained that since AI models tend to repeat the same mistakes, an attacker would need to find these bugs just once. 

“Millions of developers using the same models means the same bugs showing up across different projects,” he said. “Find one pattern in one AI codebase, you can scan for it across thousands of repositories.”

Despite its success, the team has only scratched the surface of the problem. The radar can trace metadata like co-author tags, bot emails, and other known tool signatures, but it can't identify an issue if these markers have been removed. 

The next step is behavioral detection. AI-written code has patterns in how it names variables, structures functions, and handles errors. 

“We're building models that can identify AI code from the code itself, no metadata needed,” said Zhao. “That opens up a lot of cases we currently can't touch.”

The team is also improving its verification pipeline and expanding its sources to include more vulnerability databases. The goal is to get a more complete picture of AI-introduced vulnerabilities across open source, not just the ones that happen to leave signatures behind. 

As more programmers rely on vibe coding, Zhao warns that it still needs to be reviewed as thoroughly as any other project. 

“The whole point of vibe coding is not reading it afterward, I know,” he said. “But if you're shipping AI output to production, review it the way you'd review a junior developer's pull request. Especially anything around input handling and authentication.”

When prompting AI, SSLab also recommends providing more detailed instructions to get it closer to production-ready. There are also tools to check the code for vulnerabilities after  code it has been generated. Not double-checking could lead to a catastrophe. 

“The attack surface keeps growing,” said Zhao. “More people running AI agents locally means the attacker doesn't need to break into the company infrastructure. They just need one vulnerability in a model context protocol server that someone installed and never reviewed.”

One reason the attack surfaces are expanding rapidly is AI’s evolution. In the second half of 2025, the Vibe Security Radar found about 18 cases across seven months. Then, in the first three months of 2026, it identified 56. March 2026 alone had 35, more than all of 2025 combined. 

Many tools, like Claude, are now more autonomous, allowing developers to write entire features, create files, and even make architecture decisions. 

“When an agent builds something without authentication, that's not a typo,” said Zhao. “It's a design flaw baked in from the start. Claude Code and Copilot together account for most of what we detect, but that's partly because they leave the clearest signatures.”

Now a senior professional working at the intersection of business automation and AI integration, Lane balances a high-tech career with a people-first leadership style as the head of the College’s Computing Alumni Network. In this role, she promotes mentorship, global outreach, and the "non-linear" paths that shape a successful career.

In the following Q&A, Lane shares insights from her journey from a computer science student to an AI automation expert, discusses the "human" side of technology, and outlines her vision for growing our alumni community well beyond Atlanta.

What drew you to get involved with the Computing Alumni Network?

Honestly, it started for personal reasons. I wanted to expand my network and find my people. But what kept me engaged was something deeper. I reconnected with the College about ten years ago, and I quickly realized how much I'd missed by not being involved sooner.

There's an energy you get from staying close to a place that shaped you, and I wanted to help provide that for others the way I wished it had been for me.

Can you share a moment or initiative with the Network that you’re especially proud of?

We've had some wonderful events over the years — some that really stand out, others that were quieter but no less meaningful. Reflecting on it, what I'm most proud of is how the Network has endured the turbulence of the last few years.

Navigating the pandemic, adapting to significant changes in our supporting staff, and still showing up for students and each other — that resilience is something I don't take for granted.

How has the alumni community changed since you graduated?

I can't speak to the full arc. I got involved with the Computing Network in 2019, so my perspective is more recent. What I can say is that our focus has become more centered on the students, how we can give back, and how we can include our global alumni network.

Why do you think staying connected to the College matters, even years after graduation?

I'm living proof that it's never too late and that getting involved is more than worthwhile. The relationships you build here, the sense of shared identity with people who went through something hard and came out the other side — that doesn't expire. And the further you go in your career, the more you realize how rare it is to find a community with that kind of foundation.

You’re now working in AI automation—what excites you most about your work today?

What gets me out of bed every morning is the chance to make work more human again. There's a pattern I see everywhere right now where people are being used as the connective tissue between disconnected systems — doing repetitive, manual work that drains the meaning out of their days. It's deflating in a way that's hard to overstate. I believe automation, when done right, can give people back the time and energy. If I can add some genuine meaning back to someone's workday, that's a win I'll take every time.

How did your experience as a CS student prepare you for a career in tech and business?

Georgia Tech taught me how to adapt — and more importantly, that I could. It gave me the discipline to teach myself new things, the humility to ask for help when I needed it, and the confidence to know I can do hard things. That combination has been the through-line of my entire career. The specific technical skills matter, but it's that mindset that's carried me through every pivot and challenge since.

What advice would you give to current students who hope to follow a similar path?

Find a mentor, and don't wait until you feel like you need one. The relationships you build now — with professors, with older students, with alumni — will compound in ways you can't predict.

Also, stay curious beyond your major. The most interesting problems I've worked on sit at the intersection of technology and human behavior, and I never would have found my way there if I'd kept my head down in purely technical work or kept doing only what I already knew.

How can alumni best support students and recent graduates right now?

Mentoring is the highest-leverage thing you can do, especially for students graduating into such unpredictable times. It doesn’t have to be formal or structured mentoring. Sometimes it's just about being genuinely available, replying to an email, scheduling a coffee chat, or sharing an honest picture of what your career actually looked like, not the polished version. Students need to see that the path isn't always linear, and that people who have navigated uncertainty are willing to help them do the same.

What’s next for the Network—any upcoming priorities or initiatives you’re excited about?

Our big focus right now is growth — expanding the College of Computing alumni in Atlanta and beyond. There's a lot of Georgia Tech computing talent spread across the country and the world, and we want those people to feel that this community is for them, too, not just those of us who stayed local.

Making that geographic reach feel real, not just theoretical, is something we're actively working toward.

TokenSmith is a citation-supported large language model (LLM) tutor that can be hosted locally on a user’s personal computer. The tutor only provides answers based on course materials, such as the textbook or lecture slides.  

Associate Professor Joy Arulraj began the project with support from the Bill Kent Family Foundation AI in Higher Education Faculty Fellowship last year. The fellowship, led by Georgia Tech’s Center for 21st Century Universities, supports faculty projects exploring innovative and ethical uses of AI in teaching.   

Arulraj has enlisted assistant professors Kexin Rong and Steve Mussmann to help build TokenSmith.  

Mussmann said TokenSmith is a synergistic blend of a database system and a machine learning system. The model stores textbooks, textbook annotations by course staff, common questions and answers, a learning state of the student, and student feedback in a structured database system. However, machine learning plays a key role in the answer generation as well as adapting the system to the student, course staff guidance, and user feedback.

"What excites me most is demonstrating how data-driven ML and principled database systems design can reinforce each other — one providing adaptability and flexibility, the other providing structure and traceability — in a way that benefits students," Mussmann said.

Keeping the model local has been an important focus of the project. The team wanted to create an AI tutor that helps students learn from their class resources rather than just giving answers. With each response, TokenSmith cites the origin of the answer in the provided documents.  

“One problem with LLMs is that they can hallucinate and provide wrong answers, but in this controlled environment, we can add these guardrails to make sure it’s actually helpful in an educational setting,” Rong said.  

Rong said she feels that students often undervalue textbooks, and she hopes TokenSmith can motivate students to make better use of them.  

“Textbooks can sometimes be daunting, but maybe if we combine them with the model, students might be more willing to read a paragraph or page in the textbook, and that could help clarify something for them,” she said.  

Running the model locally is more cost-effective and helps preserve the user’s privacy. But running the new tool locally comes with technical challenges.  

One challenge with creating the model is speed. Since it is a locally based model, TokenSmith depends solely on the user’s computer memory.  Tests have also shown that the tutor currently struggles to answer more complex questions. 

“We are interested in pushing the boundaries of these local models so that they give students good answers and also run fast enough to keep students engaged,” Arulraj said.  

That’s one of the main findings from a study by AI Caring on what older adults expect from explainable AI (XAI).

AI Caring is one of three AI Institutions led by Georgia Tech and funded by the National Science Foundation (NSF). The institution supports AI research that benefits older adults and their caregivers.

Niharika Mathur, a Ph.D. candidate in the School of Interactive Computing, was the lead author of a paper based on the study. The paper will be presented in April at the 2026 ACM Conference on Human Factors in Computing Systems (CHI) in Barcelona.

Mathur worked with the Cognitive Empowerment Program at Emory University to interview 23 older adults who live alone and use voice-activated AI assistants like Amazon’s Alexa and Google Home.

Many of them told her they feel excluded from the design of these products.

“The assumption is that all people want interactions the same way and across all kinds of situations, but that isn’t true,” Mathur said. “How older people use AI and what they want from it are different from what younger people prefer.”

One example she gave is that young people tend to be informal when talking with AI. Older people, on the other hand, talk to the agent like they would a person.

“If Older adults are talking to their family members about Alexa, they usually refer to Alexa as ‘she’ instead of ‘it,’” Mathur said. “They tend to humanize these systems a lot more than young people.”

Good Explanations

The study evaluated AI explanations that drew information from four sources of data:

• User history (past conversations with the agent)
• Environmental data (indoor temperature or the weather forecast)
• Activity data (how much time a user spends in different areas of the home)
• Internal reasoning (mathematical probabilities and likely outcomes)

Mathur said older users trust the agent more when it bases its explanations on data from the first three sources. However, internal reasoning creates skepticism.

Internal reasoning means the AI doesn’t have enough data from the other sources to give an explanation. It provides a percentage to reflect its confidence based on what it knows.

“The overwhelming response was negative toward confidence scores,” Mathur said. “If the AI says it’s 92% confident, older adults want to know what that’s based on.”

This is another example that Mathur said points to generational preferences.

“There’s a lot of explainable AI research that shows younger people like to see numbers in explanations, and they also tend to rely too much on explanations that contain numerical confidence. Older adults are the opposite. It makes them trust it less.”

Knowing the Context

Mathur said that AI agents interacting with older adults should serve a dual purpose. They should provide users with companionship and support independence while reducing the caretaking burden often placed on family members. 

Some studies have shown that engineers have tended to favor caretakers in the design of these tools. They prioritize daily tasks and routines, leaving some older adults to feel like they are merely a box to be checked.

She discovered that in urgent situations, older users prefer the AI to be straightforward, while in casual settings, they desire more conversation.

“How people interact with technological systems is grounded in what the stakes of the situation are,” she said. “If it had anything to do with their immediate sense of safety, they did not want conversational elaboration. They want the AI to be very direct and factual.”

Not Just Checking Boxes

Mathur said AI agents that interact with older adults are ideally constructed with a dual purpose. They should provide companionship and autonomy for the users while alleviating the burden of caretaking that is often placed on their family members. 

Some studies have shown that engineers have strayed toward favoring caretakers in the design of these tools. They prioritize daily tasks and routines, leaving some older adults to feel like they are a box to be checked.

“They’re not being thought of as consumers,” Mathur said. “A lot of products are being made for them but not with them.”

She also said psychological well-being is one of the most important outcomes these tools should produce. 

Showing older adults that they are listened to can significantly help in gaining their trust. Some interviewees told Mathur they want agents who are deliberate about understanding their preferences and don’t dismiss their questions.

Meeting these needs reduces the likelihood of protesting and creating conflict with family members.

“It highlights just how important well-designed explanations are,” she said. “We must go beyond a transparency checklist.”

That support, however, begins to disappear in these restrictive cultures once women reach menopause, according to new research from Georgia Tech

Naveena Karusala, an assistant professor in Georgia Tech’s School of Interactive Computing, and master’s student Umme Ammara are working toward improving existing technologies and designing new ones for a demographic they believe has been neglected.

Karusala and Ammara co-authored a paper based on a study they conducted with women in urban Pakistan experiencing menopause.

“Women’s health is understudied in general, but menopause is more neglected than other women’s health issues,” Karusala said. “Our choice to focus on menopause is motivated by expanding how we holistically think about women’s well-being across their lifespan.”

Karusala and Ammara will present their paper in April at the 2026 ACM Conference on Human Factors in Computing Systems (CHI) in Barcelona.

Masking Symptoms

Menopause is diagnosed after 12 consecutive months without a period, vaginal bleeding, or spotting. The transition to menopause, called perimenopause, usually happens over two to eight years.

Hormone changes may cause symptoms such as irregular periods, vaginal dryness, hot flashes, night sweats, trouble sleeping, mood swings, and brain fog.

These symptoms can be debilitating in some cases and affect daily life. However, Ammara said women are pressured to remain silent, maintain appearances, and regulate their emotions to meet social expectations.

“Understanding menopause is important because a woman would be experiencing all these symptoms, and people will not understand those as actual symptoms,” Ammara said. “There’s been resistance to the idea of the medicalization of menopause. People don’t view it as an illness, but as a life transition and something that happens naturally.”

Feeling Isolated

The women interviewed by Karusala and Ammara either stayed at home full-time or were part of the workforce.

The researchers discovered that trusted family members might be the only sources women who stay at home and do not work turn to for disclosure. 

“Women at home have the flexibility to take breaks or work at their own pace, so a lot of their experience is shaped by the emotional barriers they face,” Ammara said. 

“That could come from their husbands and family members. Some are supportive and some are not. They might weaponize it and use that term against them, or they might dismiss what they’re going through.”

Ammara said it might be easier for women in the workforce to confide in their coworkers, but explaining to an employer that they need sick leave for menopause symptoms can be intimidating.

Even in online communities that have enabled women to anonymously share their health experiences, menopause is seldom discussed.

Raising Awareness

Karusala and Ammara argue in their paper that a public health approach could be the most effective way to spark conversation about menopause in a patriarchal culture in which technology use varies.

They said the challenge in implementing technologies geared toward menopause support is that the condition isn’t well understood in public. Improving maternal health, for example, is easier to promote within these societies because of the general understanding that motherhood is important.

“There must be an existing infrastructure to build on,” Karusala said. “For example, menstrual and maternal health are taught in schools and regularly discussed in primary care. Cultural and social meaning and importance are placed on motherhood.

“A lot of that doesn’t exist for menopause. Primary care doctors are unprepared to talk about menopause compared to other health issues.”

Design Solutions

Ammara said that the most effective way for technologies to make an impact on women going through menopause is to directly address systemic power structures around women’s health within Pakistani culture.

It can start with the husbands. 

“Framing the issue for husbands to understand menopause should be at the forefront of designing technology solutions,” she said. 

“In Islamic contexts, we suggest using faith-based framings. This has been proposed for maternal health in prior works that draw on Islamic principles to engage expectant fathers in providing care and support. Framing it around religious responsibility to involve men in the journey can also be done for menopause.”

“I was placing an order from a food truck outside the College building when a student approached and asked if I remembered him,” Briana Lampert said. “It was Hoc! It took me a few moments to realize.”

Years earlier, Lampert taught Hoc Nguyen and Cardin Ho in fourth-grade language arts and reading at Hambrick Elementary School in Stone Mountain, Georgia. Today, both are computer science (CS) majors at Georgia Tech.

Nguyen first recognized Lampert’s name while searching for his academic advisor during registration. “I thought her name was familiar, but only when I met her in person did I recall she was my teacher,” he said.

Although he doesn’t remember many details from elementary school, Lampert left a lasting impression. “I remember that she was a very kind teacher and that the class liked her because of how nice she was,” he said.

After their initial meeting, Nguyen shared that Ho was also a Georgia Tech student. Lampert later ran into both students on campus while attending an event, and the three spent nearly an hour catching up.

“They were both lovely and full of personality, just as they are now. I remember how sweet and intelligent they were,” Lampert said. 

“They were very close, even then, and part of a crew that included a group of smart and talented kids. I knew they would go on to do great things, but I had no idea that any of us would end up at Tech.”

Ho also remembers Lampert’s approach in the classroom. “I remember Ms. Lampert had lots of patience,” he said. “Our class, me included, really tested her every day, yet she always maintained it to keep us on track.”

After teaching for five years, Lampert transitioned into academic advising. She started at Georgia State University in 2017 and moved to Georgia Tech in 2022. She said the move allowed her to focus on the part of education she enjoyed most.

“The part of the job that I loved the most was one-on-one interactions with students,” Lampert said. “With advising, I can provide the targeted support to students that I enjoy, but on a broad scale.”

In her current role, Lampert works closely with students as they navigate their academic journeys, while focusing on empathy and connection. She is especially passionate about supporting underrepresented student groups and helping students access campus resources.

Her experience as a teacher continues to shape her approach.

“It is important when working in higher education to remember that while Tech students are academically gifted, K-12 education does not teach a person how to ‘be a college student,’” she said. “Those skills are not inherent.”

For Nguyen, having a former teacher as an advisor has made a difference. He also enjoys reflecting on other classmates and teachers he keeps in touch with, who were part of his early academic journey.

“Having Ms. Lampert as an advisor is honestly quite nice,” he said. “It makes talking about your goals and classes a lot easier if your advisor is someone you knew from your childhood.”

Now studying CS, Nguyen discovered his interest in STEM in middle school, when he had more hands-on opportunities in science and technology.

For students considering the field, he recommends starting with personal interests. 

“CS is such a broad field that there can be some parts you don’t find interesting and others you do,” he said. “By just starting with something you like, you can enjoy the learning process more and get the skills needed.”

For Lampert, the experience highlighted the lasting impact of education across different stages of students’ journeys. 

“Hoc reminded me that, all things considered, there is a short span of time between elementary school and college,” she said. “He reaffirmed that educators are crucial at every stage of a student’s life.”

The Georgia Scientific Computing Symposium (GSCS) held its annual meeting on February 21 in Athens. Since 2009, the event has hosted researchers from across the Peach State to showcase homegrown advances in scientific computing.

The symposium highlighted Georgia’s reputation as a computing innovation hub. People from around the world come to Georgia universities to lead computing research. By advancing science, engineering, medicine, and technology, their work improves communities at home and abroad.

Faculty and students from Georgia Tech, UGA, Georgia State University, and Emory University presented at the symposium. Georgia Tech participants came from the colleges of Computing, Engineering, and Sciences.

This year’s organizers agreed to meet in Atlanta for the 2027 symposium. Georgia Tech’s School of Computational Science and Engineering (CSE) will host the 19th GSCS.

“From healthcare to computer chip design, scientific computing underpins many of the technological advances we see in our lives,” said Professor Edmond Chow, associate chair of the School of CSE.

“Scientific computing provides the mathematical models, simulations, and data‑driven tools that make modern innovation possible. It allows people to analyze complex systems, test ideas virtually before building them, and make faster, more accurate decisions across nearly every sector of society.”

Professor Haomin Zhou and Assistant Professor Helen Xu delivered two of the symposium’s five plenary talks. 

Zhou presented a new method for solving the Schrödinger equation, a landmark equation in quantum mechanics. Drawing inspiration from the mathematics used in generative artificial intelligence models, his approach develops an algorithm that more effectively simulates waves, particle motion, and other physical systems.

Xu focused on improving how computers move and organize data during complex calculations. Her work uses “cache-friendly” layouts that help computers access data more efficiently, boosting performance for scientific and engineering applications.

“Speaking at GSCS was a great opportunity,” Xu said. “The symposium fostered connections within the scientific computing community and gave us a chance to share exciting research.”

The symposium showcased student work through a poster blitz and a poster session. During the blitz, 36 students each had one minute to introduce their research to the full audience. They then shared more details about their research during the poster session.

The student projects showed the range of fields supported by scientific computing. The session also provided attendees with an opportunity to connect and expand their professional networks, helping grow the field’s future impact.

“As an aerospace engineer by training and aspiring computational scientist, GSCS gave me the platform to network with other researchers in the field while showcasing my own research,” said M.S. student Kashvi Mundra. 

“I was able to connect with scientists across different disciplines whose work intersects with my own in unexpected ways. Those conversations pushed my thinking beyond my own lab's perspective, helping me see my work on physics-informed machine learning for inverse problems in a broader scientific computing context.”

Georgia Tech students who presented posters included:

Abir Haque (CSE), Massively Parallel Random Phase Approximation Correlation Energy via Lanczos Quadrature

Antonio Varagnolo (CSE), Physics-Enhanced Deep Surrogates for the Phonon Boltzmann Transport Equation

Ben Burns (CSE), Infinite-Dimensional Stein Variational Inference with Derivative-Informed Neural Operators

Ben Wilfong (CSE), Shocks without Shock Capturing; Compressible Flow at 1 quadrillion Degrees of Freedom without Loss of Accuracy

Daniel Vickers (CSE), Highly-Parallel Fluid-Solid Interactions for Compressible Flows

Eric Fowler (CSE), High-Performance Tensor Contractions in Computational Chemistry

Haoran Yan (Math), Understanding Denoising Autoencoders through the Manifold Hypothesis: A Geometric Perspective

Kashvi Mundra (CSE), Autoregressive Multifidelity Neural Surrogate Modeling under Scarce Data Regimes

Sebastián Gutiérrez Hernández (Math/CSE), PDPO: Parametric Density Path Optimization

Vivian Zhang (AE), Multifidelity Operator Inference: Non-Intrusive Reduced Order Modeling from Scarce Data

Xian Mae Hadia (CSE), Data Efficiency of Surrogate Models: Learning Physics Data from Full Field Data vs. Inductive Bias from Approximate PDE Solvers

Xiangming Huang (CSE), Neural Operator Accelerated Evolutionary Strategies for PDE-Constraint Optimization

Zhaiming Shen (Math), Understanding In-Context Learning on Structured Manifolds: Bridging Attention to Kernel Methods

Zhongjie Shi (Math), Towards Understanding Generalization in DP-GD: A Case Study in Training Two-Layer CNNs

New cybersecurity research from the Georgia Institute of Technology, however, revealed that crews aboard commercial vessels were often not adequately prepared to manage cyberattacks effectively due to systemic training gaps.

The findings are based on interviews conducted by researchers with more than 20 officer-level mariners to assess the maritime industry’s readiness to handle cybersecurity attacks at sea.

"Historically, cybersecurity research has focused heavily on cyber-physical systems like cars, factories, and industrial plants, but ships have largely been overlooked,” said Anna Raymaker, Ph.D. student and lead researcher.

“That gap is concerning when more than 90% of the world’s goods travel by sea. Recent incidents, from GPS spoofing to ships linked to subsea cable disruptions, show that maritime systems are increasingly part of the global cyber threat landscape.”

The researchers proposed four practical strategies to strengthen maritime cyber defenses and close the training gaps. Their findings were presented recently at the ACM SIGSAC Conference on Computer and Communications Security (CCS).

1. Make Cybersecurity Training Actually Maritime

Many of those interviewed for the study described current cybersecurity training as “boilerplate” — generic modules that don’t reflect real shipboard risks. 

Researchers recommend:

• Role-specific instruction: Navigation officers should learn to detect and identify GPS spoofing. Engineers should focus on vulnerabilities in remotely monitored systems.
• Bridging IT and Operational Technology: Crews need to understand how attacks on IT systems can trigger physical consequences in operational technology — including collisions, groundings, or explosions.
• Hands-on delivery: Replace passive PowerPoints with drills and in-person exercises that build muscle memory.
• Accessible standards: Training must account for the wide range of educational backgrounds across crews and be standardized across ranks.

2. Move Beyond “Call IT”

At sea, crews can’t simply escalate a cyber incident to a shore-based IT department and wait. Operational resilience requires onboard readiness.

Researchers recommend:

• Vessel-specific response plans: Ships need clear, actionable protocols for threats such as AIS jamming or radar manipulation.
• Military-style drills: Adopting MCON (Emission Control) exercises — used by the U.S. Military Sealift Command — can train crews to operate safely without electronic systems.
• Stronger connectivity controls: High-bandwidth satellite systems like Starlink introduce new risks. Clear policies and network segregation are essential to prevent new entry points for attackers.

Related Article: When GPS lies at sea: How electronic warfare is threatening ships and their crews by Anna Raymaker

3. Create Unified, Ship-Specific Regulations

Maritime cybersecurity regulations are often reactive and fragmented. Researchers argue the industry needs a cohesive, domain-specific framework.

Key recommendations include:

• A unified global model: Like the energy sector’s NERC CIP standards, a maritime framework could mandate baseline controls such as encryption, network segmentation, and anonymous incident reporting.
• Rules built for real crews: Regulations designed for large naval operations don’t translate well to smaller merchant or research vessels. Standards must reflect actual shipboard conditions.
• Future-proofing requirements: Autonomous ships and remotely operated vessels expand the cyber-physical attack surface. Regulations must proactively address these emerging technologies.

4. Invest in Maritime-Specific Cyber Research

Finally, the researchers stress that long-term resilience requires deeper technical research focused on maritime systems.

Priority areas include:

• Real-time intrusion detection systems tailored to shipboard protocols.
• Proactive security risk assessments of interconnected onboard systems.
• Cyber-physical modeling to better understand cascading failures in complex maritime environments.

The Bottom Line

Cyber threats at sea are no longer hypothetical. Mariners report real-world incidents ranging from GPS spoofing to ransomware that disrupts global trade.

“Through our interviews with mariners, I saw firsthand how much dedication and pride they take in their work,” said Raymaker. “Our goal is for this research to serve as a call to action for researchers, policymakers, and industry to invest more attention in maritime cybersecurity and support the people who risk their lives every day to keep global trade, food, and energy moving."

A Sea of Cyber Threats: Maritime Cybersecurity from the Perspective of Mariners was presented at CCS 2025. It was written by Raymaker and her colleagues, Ph.D. students Akshaya Kumar, Miuyin Yong Wong, and Ryan Pickren; Research Scientist Animesh Chhotaray, Associate Professor Frank Li, Associate Professor Saman Zonouz, and Georgia Tech Provost and Executive Vice President for Academic Affairs Raheem Beyah.

Li, an accomplished computer security and privacy researcher, joined Georgia Tech in 2020 as the Institute was launching the School of Cybersecurity and Privacy (SCP). He holds a joint appointment with the School of Electrical and Computer Engineering (ECE). 

“While tenure may be an individual's milestone, in reality, it reflects the help, support, and hard work of countless others,” Li said.

He credits his accomplishments to the ongoing mentorship and support he has received from faculty and staff at SCP, ECE, and Georgia Tech.

“I'm also extremely thankful to work with such amazing students at Georgia Tech, especially the Ph.D. students in my research lab, and the BS and MS students in my classes, who help our research efforts. Georgia Tech has been an amazing place to start my faculty career,” said Li.

Li advises five Ph.D. students at his Better Empirically Established Security (BEES) lab in SCP. They take a data-driven approach to understanding how security and privacy concerns manifest in practice, and use the insights gained to drive improvements in real-world security.

Their research examines how users, security operators, and attackers behave in various security and privacy-sensitive situations, often using internet-wide measurements, network traffic analysis, user studies and experiments, and large-scale data mining.

“The tenure and promotion to associate professor rank is in recognition of the outstanding research program Frank has developed at SCP,” said Mustaque Ahamad, interim chair and Regents’ Entrepreneur.

“He is an award-winning educator. We look forward to his continued leadership in the important areas of usable security and network security in the future.”

Li was among nine College of Computing faculty members who received promotion and tenure this year.

John P. Imlay Jr. Dean of Computing Vivek Sarkar emailed the College community with the good news.

“We are truly thrilled to celebrate this moment with you, as we recognize your contributions to our students and to the advancement of our College and Institute in so many ways,” he said.

In 2025, Li received the prestigious CAREER Award from the National Science Foundation (NSF). His CAREER project will investigate real-world uses of FIDO2/passkeys and address security and usability issues that can arise. A goal of his research is to identify and resolve problems before they become widespread and more difficult to solve.

A new mobile app will soon put the ability to monitor a baby’s prenatal heartbeat in the hands of pregnant women who may worry about their baby’s health in between doctor’s visits. 

In the International Disaster Reconnaissance (IDR) course, students now use Filio, a platform built by School of Computing Instruction Senior Lecturer Max Mahdi Roozbahani, to capture immersive 360° media, photos, and video that transform real disaster sites in India and Nepal into living digital classrooms. 

Offered by the School of Civil and Environmental Engineering and taught by IDR director and Regents’ Professor David Frost, the course pairs traditional fieldwork with Roozbahani’s expertise in immersive technology and data-driven learning, transforming on-the-ground observations into reusable, interactive educational resources. 

How Computing Can Capture Data 

Disasters are not only physical events; they are also information events, Roozbahani says. Effective response and long-term resilience depend on the ability to observe, record, and communicate critical data under pressure. Georgia Tech’s IDR course pairs structured on-campus preparation with international field experiences, enabling students to study the cascading effects of major disasters, including how local building practices, governance, and culture shape damage and recovery. 

“When students step into a disaster zone, they learn quickly that resilience is a systems problem: physical, social, and informational. Our job in computing is to help them capture and reason about that system responsibly,” Roozbahani said. 

Learning from the 2025 Himalayas Expedition 

During spring break last year, the cohort traveled along the Teesta River corridor in Sikkim, India. The region is shaped by steep terrain, fast-moving water, and critical infrastructure in narrow valleys. 

The visit followed the October 2023 glacial lake outburst flood from South Lhonak Lake, which destroyed the Teesta III hydropower dam and impacted downstream towns, including Dikchu and Rangpo. Field stops across India included Lachung, Chungthang, Dikchu, Rangpo, Gangtok, and New Delhi. 

Students explored both upstream and downstream consequences. 

Upstream, the team examined how steep terrain and river confinement amplify flood forces, creating cascading risks for infrastructure. Using Filio’s interactive 360° media, students captured conditions in Lachung and Chungthang, allowing viewers to explore the landscape through a 360° photo and 360° video that reveal how topography and river dynamics intensify disaster impacts. 

They studied community-scale effects downstream, including damaged buildings, disrupted access, and prolonged recovery timelines. 

Rangpo offered a glimpse of recovery in motion, with materials staged for rebuilding bridges and roads essential to commerce and emergency response.

Indoor farms, also known as vertical farms, are popular among agricultural researchers and are expanding across the agricultural industry. Some benefits they have over outdoor farms include:

• Year-round production of food crops
• Less water and land requirements
• Not needing pesticides
• Reducing carbon emissions from shipping
• Reducing food waste

Additionally, some studies indicate that indoor farms produce more nutritious food for urban communities. 

However, these farms are often inaccessible to birds, bees, and other natural pollinators, leaving the pollination process to humans. The tedious process must be completed by hand for each flower to ensure the indoor crop flourishes.

Ai-Ping Hu, a principal research engineer at the Georgia Tech Research Institute (GTRI), has spent years exploring methods to efficiently pollinate flowering plants and food crops in indoor farms to find a way to efficiently pollinate flower plants and food crops in indoor farms.

Hu, Assistant Professor Shreyas Kousik of the George W. Woodruff School of Mechanical Engineering, and a rotating group of student interns have developed a robot prototype that may be up to the task.

The robot can efficiently pollinate plants that have both male and female reproductive parts. These plants only require pollen to be transferred from one part to the other rather than externally from another flower.

Natural pollinators perform this task outdoors, but Hu said indoor farmers often use a paintbrush or electric tootbrush to ensure these flowers are pollinated. 

Knowing the Pose

An early challenge the research team addressed was teaching the robot to identify the “pose” of each flower. Pose refers to a flower’s orientation, shape, and symmetry. Knowing these details ensures precise delivery of the pollen to maximize reproductive success. 

“It’s crucial to know exactly which way the flowers are facing,” Hu said.

“You want to approach the flower from the front because that’s where all the biological structures are. Knowing the pose tells you where the stem is. Our device grasps the stem and shakes it to dislodge the pollen.

“Every flower is going to have its own pose, and you need to know what that is within at least 10 degrees.”

Computer Vision Breakthrough

Harsh Muriki is a robotics master’s student at Georgia Tech’s School of Interactive Computing, who used computer vision to solve the pose problem while interning for Hu and GTRI.

Muriki attached a camera to a FarmBot to capture images of strawberry plants from dozens of angles in a small garden in front of Georgia Tech’s Food Processing Technology Building. The FarmBot is an XYZ-axis robot that waters and sprays pesticides on outdoor gardens, though it is not capable of pollination.

“We reconstruct the images of the flower into a 3D model and use a technique that converts the 3D model into multiple 2D images with depth information,” Muriki said. “This enables us to send them to object detectors.”

Muriki said he used a real-time object detection system called YOLO (You Only Look Once) to classify objects. YOLO is known for identifying and classifying objects in a single pass.

Ved Sengupta, a computer engineering major who interned with Muriki, fine-tuned the algorithms that converted 3D images into 2D.

“This was a crucial part of making robot pollination possible,” Sengupta said. “There is a big gap between 3D and 2D image processing.

“There’s not a lot of data on the internet for 3D object detection, but there’s a ton for 2D. We were able to get great results from the converted images, and I think any sector of technology can take advantage of that.”

Sengupta, Muriki, and Hu co-authored a paper about their work that was accepted to the 2025 International Conference on Robotics and Automation (ICRA) in Atlanta.

Measuring Success

The pollination robot, built in Kousik’s Safe Robotics Lab, is now in the prototype phase. 

Hu said the robot can do more than pollinate. It can also analyze each flower to determine how well it was pollinated and whether the chances for reproduction are high.

“It has an additional capability of microscopic inspection,” Hu said. “It’s the first device we know of that provides visual feedback on how well a flower was pollinated.”

For more information about the robot, visit the Safe Robotics Lab project page.

Georgia Stoica is one of 38 Ph.D. students worldwide researching machine learning who were named a 2025 Google Ph.D. Fellow.

Stoica is designing AI training methods that bypass fine-tuning, which is the process of adapting a large pre-trained model to perform new tasks. Fine-tuning is one of the most common ways engineers update large-language models like ChatGPT, Gemini, and Claude to add new capabilities. 

If an AI company wants to give a model a new capability, it could create a new model from scratch for that specific purpose. However, if the model already has relevant training and knowledge of the new task, fine-tuning is cheaper.

Stoica argues that fine-tuning still uses large amounts of data, and that other methods can help models learn more effectively and efficiently.

“Full fine-tuning yields strong performance, but it can be costly, and it risks catastrophic forgetting,” Stoica said. “My research asks if we can extend a model’s capabilities by imbuing it with the expertise of others, without fine-tuning?

“Reducing cost and improving efficiency is more important than ever. We have so many publicly available models that have been trained to solve a variety of tasks. It’s redundant to train a new model from scratch. It’s much more efficient to leverage the information that already exists to get a model up to speed.”

Stoica said the solution is a cost-effective method called model merging. This method combines two or more AI models into a single model, improving performance without fine-tuning.

On a basic level, Stoica said an example would be combining a model that is efficient at classifying cats with one that works well at dogs.

“Merging is cheap because you just take the parameters, the weights of your existing models, and combine them,” he said. “You could take the average of the weights to create a new model, but that sometimes doesn’t work. My work has aimed to rearrange the weights so they can communicate easily with each other.”

Through his Google fellowship, Stoica seeks to apply model merging to create a cutting-edge vision encoder. A vision encoder converts image or video data into numerical representations that computers can understand. This enables tasks such as image or facial recognition and generative image captioning.

“I want to be at the frontier of the field, and Google is clearly part of that,” Stoica said. “The vision encoder is very large-scale, and Google has the infrastructure to accommodate it.”

Georgia Tech’s Qi Tang is building machine learning (ML) models to accelerate nuclear fusion research, making it more affordable and more accurate. Backed by a grant from the U.S. Department of Energy (DOE), Tang’s work brings clean, sustainable energy closer to reality.

Tang has received an Early Career Research Program (ECRP) award from the DOE Office of Science. The grant supports Tang with $875,000 disbursed over five years to craft ML and data processing tools that help scientists analyze massive datasets from nuclear experiments and simulations.

Tang is the first faculty member from Georgia Tech’s College of Computing and School of Computational Science and Engineering (CSE) to receive the ECRP. He is the seventh Georgia Tech researcher to earn the award and the only GT awardee among this year’s 99 recipients.

More than a milestone, the award reflects a shift in how nuclear research is done. Today, progress depends on computing and data science as much as on physics and engineering.

“I am honored and excited to receive the ECRP award through DOE’s Advanced Scientific Computing Research program, an organization I care about deeply,” said Tang, an assistant professor in the School of CSE. 

“I am grateful to my former colleagues at Los Alamos National Laboratory and collaborators at other national laboratories, including Lawrence Livermore, Sandia, and Argonne. I am also thankful for my Ph.D. students at Georgia Tech, whose dedication and creativity make this award possible.”

[Related: New Faculty Applies High-Performance Computing, Scientific Machine Learning Interests to Studies in Plasma Physics]

A problem in nuclear research is that fusion simulations are challenging to understand and use. These simulations generate enormous datasets that are too large to store, move, and analyze efficiently.

In his ECRP proposal to DOE, Tang introduced new ML methods to improve the analysis and storage of particle data.

Tang’s approach balances shrinking data so it is easier to store and transfer while preserving the most important scientific features. His multiscale ML models are informed by physics, so the reduced data still reflects how fusion systems really behave.

With Tang’s research, scientists can run larger, more realistic fusion models and analyze results more quickly. This accelerates progress toward practical fusion energy.

“In contrast to generic black-box-type compression tools, we aim at preserving the intrinsic structures of the particle dataset during the data reduction processes,” Tang said. 

“Taking this approach, we can meet our goal of achieving high-fidelity preservation of critical physics with minimum loss of information.”

Computing is essential in modern research because of the amount of data produced and captured from experiments and simulations. In the era of exascale supercomputers, data movement is a greater bottleneck than actual computation.

DOE operates three of the world’s four exascale supercomputers. These machines can calculate one quintillion (a billion billion) operations per second.

The exascale era began in 2022 with the launch of Frontier at Oak Ridge National Laboratory. Aurora followed in 2023 at Argonne National Laboratory. El Capitan arrived in 2024 at Lawrence Livermore National Laboratory.

With Tang’s data reduction approaches, all of DOE’s supercomputers spend more time on science and less time waiting for data transfers.

“Qi’s work in computational plasma physics and nuclear fusion modeling has been groundbreaking,” said Haesun Park, Regents’ Professor and Chair of the School of CSE. 

“We are proud of Qi and what this award means for him, Georgia Tech, and the Department of Energy toward leveraging computation to solve challenges in science and engineering, such as sustainable energy."

Previous Georgia Tech recipients of DOE Early Career Research Program awards include:

Itamar Kimchi, assistant professor, School of Physics

Sourabh Saha, assistant professor, George W. Woodruff School of Mechanical Engineering

Wenjing Lao, associate professor, School of Mathematics

Ryan Lively, Thomas C. DeLoach Professor, School of Chemical & Biomolecular Engineering

Josh Kacher, associate professor, School of Materials Science and Engineering

Devesh Ranjan, Eugene C. Gwaltney Jr. School Chair and professor, Woodruff School of Mechanical Engineering

“The first time I worked on a computer there and wrote my first program, I was hooked,” he said. 

“There is something uniquely satisfying about seeing the immediate results of your work. I also appreciated how objective coding is. It either works or it does not.” 

Musaev’s journey in CS continued at Kyrgyz-Russian Slavic University, where a chance discovery set the stage for his academic path abroad. After spotting a leaflet for a presidential scholarship, he applied and was among the ten winners out of roughly 1,500 applicants. 

“As part of the scholarship, the organizers selected an American university for me, Georgia Institute of Technology, which I had not heard of at the time,” he said. 

At Tech, Musaev earned his bachelor’s in CS. He later continued his studies as a graduate research assistant and earned his master’s in CS. 

That early fascination with problem-solving and clarity continues to shape Musaev’s approach to teaching today. As a lecturer in the School of Computing Instruction (SCI), he teaches CS 2316 Data Input and Manipulation and his favorite course, CS 1331 Introduction to Object-Oriented Programming. 

“From the moment I started teaching it, something just felt natural,” he said. “I enjoy coding live in class, watching students grasp new ideas, and explaining not only how things work, but why they were designed that way.” 

Although Musaev is now rooted in academia, his career has included significant time in industry. After completing his degrees, he worked at Siebel Systems, where he developed customer relationship management software and helped transition a flagship product from desktop to the web. He then returned to Kyrgyzstan to found and manage a successful software company before returning to the United States to earn his Ph.D. 

He believes those experiences provide perspective that cannot be learned in a classroom alone. 

“My advice may be nontraditional,” he said. “Spend time in industry. Seeing how the concepts you teach are applied in practice provides an invaluable perspective. This is something you simply cannot gain from textbooks alone.” 

Since joining SCI in January 2020, Musaev has found a strong sense of community. 

“I am very happy to be part of this team,” he said. “Everyone is supportive and willing to help. It truly feels like a collaborative environment.” 

For Musaev, the most meaningful moments come from students, often unexpectedly. 

“Recently, I was walking with a head TA discussing course-related topics when a student suddenly stepped in front of us and interrupted our conversation. He told me I was the best professor he had ever had. Moments like that are difficult to put into words, but they mean everything to us as instructors,” he said. 

He said he hopes students find value in his classes and leave each lecture having learned something new.  

“I also want them to genuinely enjoy CS. It is an incredible field, and I cannot imagine doing anything else.” 

Associate Professor Jessica Roberts and Ph.D. student Emily Amspoker of Georgia Tech’s School of Interactive Computing are working with the University of Georgia’s Marine Extension and Georgia Sea Grant in Savannah. Together, they’ve developed a prototype display that uses sonification and texture to convey sea floor habitat information from Gray’s Reef National Marine Sanctuary off the coast of Georgia.

Sonification is the process of translating data points into sound.

The display functions as a map that BLV users can follow to learn about each habitat. It is made from a wooden board with laser-cut patterns engraved into the surface. Each pattern represents information about the four types of habitats found in Gray’s Reef. Each pattern has a distinct sound that corresponds to a legend on the board, which provides an audio description of each habitat.

The four habitats are:

• Flat sand — smooth sandy seafloor with little topographic variation that provides habitat for burrowing organisms such as worms, clams, and sand dollars.
• Rippled sand — sandy bottom shaped into small wave-like ridges by currents and wave action; supports microhabitats of small invertebrates and attracts fish feeding on buried prey.
• Sparse live bottom — areas of exposed hard surfaces with scattered attached organisms like sponges, corals, and algae, offering structure and shelter for reef-associated fish and invertebrates.
• Dense live bottom — hard-bottom reef areas with abundant attached marine life, providing high biodiversity and offering food, and breeding sites for numerous species.

By allowing learners to explore these habitats, the team hopes to emphasize the importance of protecting diverse ocean habitats. 

“Our job was to figure out how we can use sounds and touch to represent each of the four habitat types so our visitors can explore the ocean without being able to see it,” she said.

Roberts said the project is critical to advance understanding of how science and informal learning can be more inclusive to those who have difficulty processing visual data displays.

Ryan Punamiya (CS 2025) and Summer Abramson, a third-year computational media student, have been honored by the Computing Research Association (CRA) through its 2025–2026 Outstanding Undergraduate Researcher Award (URA) program. 

Punamiya was named a runner-up for the prestigious award, while Abramson received an honorable mention among hundreds of applicants from universities across North America. 

The CRA Outstanding Undergraduate Researcher Award program recognized eight awardees in 2026, along with eight runners-up, nine finalists, and over 200 honorable mentions from thousands of applications.  

Advancing Robotics Research 

Punamiya knew early on that he didn’t want to wait until starting his Ph.D. to do meaningful and impactful robotics research.  

Punamiya joined the Robot Learning and Reasoning Lab (RL2) directed by Assistant Professor Danfei Xu. While there, he contributed to the lab’s Meta-sponsored EgoMimic project, which trains robots to perform human tasks using recordings captured by Meta’s Project Aria research glasses. 

Punamiya is also the first author of a paper accepted to the 2025 Conference on Neural Information Processing Systems (NeurIPS), one of the world’s most prestigious artificial intelligence (AI) and machine learning conferences. 

“Ryan is the strongest undergraduate I've worked with,” Xu said, “including students who went on to Stanford, Berkeley, and leadership roles in major tech companies. He’s already operating at the level of a strong third-year Ph.D. student.” 

Punamiya said it was a challenge to balance his undergraduate coursework with his research in Xu’s lab. 

“You get out how much you put in,” he said. “I built my class schedule to give myself as much time to do research as possible. It also boils down to having the right research mentors. 

“(Xu) never saw me as an undergrad who’s just there to do grunt work. I was fortunate he saw my curiosity and cultivated me as a researcher. That’s really how you get more undergrads motivated to research — giving them the chance to be independent and explore ideas of their own.” 

Punamiya said his work in Xu’s lab has already helped him identify the research areas he wants to focus on as he considers his next steps. He will continue developing generalized training models for robots using human data so they can perform tasks instantly upon deployment. 

"The amount of data needed to train a robot is difficult to obtain even for top industry companies," he said. "We have embodied robot data available in billions of humans. With the advent of extended reality devices, we can get a scalable source of diverse interactions within environments."

Punamiya graduated in December and recently started an internship at Nvidia. He mentioned he has been accepted into several Ph.D. programs, including Georgia Tech, and he is choosing where to continue his research. 

“It’s the first time my research has been acknowledged externally by the robotics community,” he said. “It’s good to know the problem I’m working on is important, and that motivates me. Robotics is an exciting field. We are doing things now that two years ago were difficult to do.” 

Researching Inclusion in Computing Education 

Abramson conducts research in the People-Agents Research for Computing Education (PARCE) Laboratory under the mentorship of Pedro Guillermo Feijóo-García, a faculty member in the School of Computing Instruction. He and the Associate Dean for Undergraduate Education, Olufisayo Omojokun, nominated her for the award. 

Her work focuses on the intersection of computing education and human-AI interaction, where she’s been exploring ways to create more equitable technology. 

“This is such a huge milestone, and I couldn't be prouder of Summer,” Feijóo-García said. “Mentoring her for almost two years has been an amazing experience.” 

Abramson has received the Georgia Tech President’s Undergraduate Research Award (PURA) twice, which supports her research exploring how user-centered design curricula can help address attrition among women in computing.

“I’ve had the amazing opportunity to pursue research at the intersection of student identity, community belonging, and how we can build tools that support our diverse student population,” Abramson said. 

“Dr. Pedro and I have a goal to build community through a human-first approach, and I could not be more grateful for his support and guidance in my own journey. The CRA highlights the best of what the computing discipline has to offer, and I am incredibly honored for our work to be recognized.”

Abramson will spend the summer researching how user-centered design curricula can help promote confidence, belonging, and retention for women in computing.

Nominees for the PURA program were recognized for contributing to multiple research projects, authoring or coauthoring papers, presenting at conferences, developing widely used software artifacts, and supporting their communities as teaching assistants, tutors, and mentors. 

School of Computing Instruction Communications Officer Emily Smith contributed to this story.

Main Photo: Ryan Punamiya works with a robot during the 2025 International Conference on Robotics and Automation in Atlanta. Photo by Terence Rushin/College of Computing.

Professor Munmun De Choudhury is one of eight experts serving on the initial council. OpenAI invited De Choudhury for her expertise on how digital resources affect youth mental health.

When the first cryptocurrency, Bitcoin, was proposed in 2008, the goal was simple: to create a digital currency free from banks and governments. Over time, that idea evolved into something much bigger: “decentralized finance,” or “DeFi.”

With decentralized finance, people trade, borrow and earn interest on crypto assets without relying on traditional intermediaries. DeFi services run on blockchains, which are essentially digital ledgers, and use “smart contracts” − self-executing code that automates financial transactions. Tens of billions of dollars have poured into the DeFi market.

But with innovation comes risks. The lack of centralized oversight has made crypto, including decentralized finance, a prime target for hackers and scammers. In 2024 alone, people lost nearly US$1.5 billion due to security exploits and fraud. And unlike traditional finance, there’s usually no way to recover stolen crypto.

As a computer scientist, I wanted to better understand how people perceive and respond to these risks. So my colleagues and I first conducted in-depth interviews with 14 crypto investors, then surveyed nearly 500 others to validate our findings.

Our study found that people often made the same mistakes, driven by recurring misconceptions and gaps in security awareness. Here are some of the most important.

Mistake 1: Thinking the blockchain guarantees security

Many people told us they thought decentralized finance was secure – but their reasoning wasn’t very convincing. Some seemed to confuse decentralized finance with blockchain technology itself, which is designed to ensure transactions are tamper-resistant through so-called “consensus mechanisms.” One told us that DeFi is secure “because a hacker would have to override an entire blockchain” to steal funds.

But services on the blockchain are still vulnerable to implementation and design flaws. These include smart contract breaches, in which bad guys exploit bugs in a service’s code, and front-end attacks, where a user interface is altered to redirect funds into a hacker’s wallet. A front-end attack was reportedly to blame for a recent $1.5 billion crypto heist.

Mistake 2: Thinking safe keys mean safe funds

Another common misconception is that DeFi is secure if private keys are well stored. A private key is a secret code that allows someone to access their crypto assets. It’s true that in DeFi – unlike in centralized crypto finance where an exchange holds private keys – users have full control over their own private keys.

But even with perfect private key management, users can still lose funds by interacting with compromised DeFi platforms. That’s because safeguarding private keys can prevent only direct attacks targeting private key access, such as phishing attempts.

The people we spoke with also failed to follow best practices for securing their private keys. Using a hardware wallet – a physical device that stores private keys offline – is one of the most secure options for protecting keys from online threats. However, our study found that only a handful of participants actually used hardware wallets.

Mistake 3: Thinking 2-factor authentication is a silver bullet

Two-factor authentication, or 2FA, is a standard security mechanism in which two forms of verification are required to access an account. Think being texted a one-time code before you can log into your bank account.

To prevent account breaches, centralized crypto exchanges such as Binance and Coinbase use two-factor authentication for logins, account recovery and withdrawal confirmations. But while 2FA is crucial to security in the traditional and centralized crypto finance system, it plays a much smaller role in decentralized finance.

DeFi wallets give users access based on private key ownership rather than identity verification, which means traditional 2FA can’t be used. Instead, only 2FA-like mechanisms are available in DeFi. For instance, multisignature wallets require approval from multiple private key holders. However, if your private key is compromised, attackers can perform wallet operations on your behalf without any additional verification. In addition, even users who adopt 2FA-like measures can’t prevent the security breaches on the DeFi services’ end.

Unfortunately, our participants were overly confident regarding the effectiveness of 2FA, with one saying, “Two-factor authentication has been one of the best solutions for keeping wallets safe.” In our survey, 57.1% of users relied on 2FA as their only technical countermeasure against rug pulls – scams where project creators suddenly withdraw funds – and 49.3% did so for smart contract exploits. This misplaced trust could lead them to ignore more effective security strategies.

Mistake 4: Not managing token approvals

One such effective strategy is revoking token approvals. In DeFi, tokens are digital assets on a blockchain that represent value or rights, and users often need to approve smart contracts to access or spend them. But if you leave these approvals open, a malicious contract – or one that’s been hacked – can drain your wallet. So it’s crucial to routinely check all token approvals you’ve granted to prevent losses caused by fraudulent or hacked DeFi services. Specifically, you should limit spending allowances instead of using the default “unlimited” option, and revoke approvals for apps you no longer use or trust.

Worryingly, we found that only 10.8% and 16.3% of participants regularly checked and revoked token approvals to protect against rug pulls and smart contract exploits, respectively. In light of this, we recommend that wallet providers introduce a reminder feature to prompt users to review their token approvals periodically.

Mistake 5: Not learning from past incidents

Even after they’re hacked or scammed, people often don’t do anything to improve their security practices, we found. Just 17.6% of those who reported being victims of a DeFi scam regularly checked token approvals afterward. Worse, 26% took no action at all after a scam, and 16.4% doubled down by investing even more in other DeFi services.

Surprisingly, more than half of the victims said their belief in DeFi either stayed the same or grew stronger after the incident. One user who lost $4,700 due to a rug-pull incident said, “My belief in cryptocurrency has grown stronger after that because I made good money from it.” That person added, “An opportunity to make money is something I believe in.” This suggests that DeFi users’ financial motivations can sometimes outweigh their security concerns – and, perhaps, their better judgment.

There’s no one-size-fits-all solution to DeFi security. But awareness is the first step. To stay safe, crypto investors should use hardware wallets, revoke unused token approvals and continually learn new techniques to protect themselves from evolving threats. Most importantly, they should stay rational and not let the allure of profits cloud their security practices.

This article is republished from The Conversation under a Creative Commons license. Read the original article.

Nearly half of Americans, both Democrats and Republicans, question whether elections are conducted fairly. Some voters accept election results only when their side wins. The problem isn’t just political polarization – it’s a creeping erosion of trust in the machinery of democracy itself.

Commentators blame ideological tribalism, misinformation campaigns and partisan echo chambers for this crisis of trust. But these explanations miss a critical piece of the puzzle: a growing unease with the digital infrastructure that now underpins nearly every aspect of how Americans vote.

The digital transformation of American elections has been swift and sweeping. Just two decades ago, most people voted using mechanical levers or punch cards. Today, over 95% of ballots are counted electronically. Digital systems have replaced poll books, taken over voter identity verification processes and are integrated into registration, counting, auditing and voting systems.

This technological leap has made voting more accessible and efficient, and sometimes more secure. But these new systems are also more complex. And that complexity plays into the hands of those looking to undermine democracy.

In recent years, authoritarian regimes have refined a chillingly effective strategy to chip away at Americans’ faith in democracy by relentlessly sowing doubt about the tools U.S. states use to conduct elections. It’s a sustained campaign to fracture civic faith and make Americans believe that democracy is rigged, especially when their side loses.

This is not cyberwar in the traditional sense. There’s no evidence that anyone has managed to break into voting machines and alter votes. But cyberattacks on election systems don’t need to succeed to have an effect. Even a single failed intrusion, magnified by sensational headlines and political echo chambers, is enough to shake public trust. By feeding into existing anxiety about the complexity and opacity of digital systems, adversaries create fertile ground for disinformation and conspiracy theories.

Testing Cyber Fears

To test this dynamic, we launched a study to uncover precisely how cyberattacks corroded trust in the vote during the 2024 U.S. presidential race. We surveyed more than 3,000 voters before and after election day, testing them using a series of fictional but highly realistic breaking news reports depicting cyberattacks against critical infrastructure. We randomly assigned participants to watch different types of news reports: some depicting cyberattacks on election systems, others on unrelated infrastructure such as the power grid, and a third, neutral control group.

The results, which are under peer review, were both striking and sobering. Mere exposure to reports of cyberattacks undermined trust in the electoral process – regardless of partisanship. Voters who supported the losing candidate experienced the greatest drop in trust, with two-thirds of Democratic voters showing heightened skepticism toward the election results.

But winners too showed diminished confidence. Even though most Republican voters, buoyed by their victory, accepted the overall security of the election, the majority of those who viewed news reports about cyberattacks remained suspicious.

The attacks didn’t even have to be related to the election. Even cyberattacks against critical infrastructure such as utilities had spillover effects. Voters seemed to extrapolate: “If the power grid can be hacked, why should I believe that voting machines are secure?”

Strikingly, voters who used digital machines to cast their ballots were the most rattled. For this group of people, belief in the accuracy of the vote count fell by nearly twice as much as that of voters who cast their ballots by mail and who didn’t use any technology. Their firsthand experience with the sorts of systems being portrayed as vulnerable personalized the threat.

It’s not hard to see why. When you’ve just used a touchscreen to vote, and then you see a news report about a digital system being breached, the leap in logic isn’t far.

Our data suggests that in a digital society, perceptions of trust – and distrust – are fluid, contagious and easily activated. The cyber domain isn’t just about networks and code. It’s also about emotions: fear, vulnerability and uncertainty.

Firewall of Trust

Does this mean we should scrap electronic voting machines? Not necessarily.

Every election system, digital or analog, has flaws. And in many respects, today’s high-tech systems have solved the problems of the past with voter-verifiable paper ballots. Modern voting machines reduce human error, increase accessibility and speed up the vote count. No one misses the hanging chads of 2000.

But technology, no matter how advanced, cannot instill legitimacy on its own. It must be paired with something harder to code: public trust. In an environment where foreign adversaries amplify every flaw, cyberattacks can trigger spirals of suspicion. It is no longer enough for elections to be secure − voters must also perceive them to be secure.

That’s why public education surrounding elections is now as vital to election security as firewalls and encrypted networks. It’s vital that voters understand how elections are run, how they’re protected and how failures are caught and corrected. Election officials, civil society groups and researchers can teach how audits work, host open-source verification demonstrations and ensure that high-tech electoral processes are comprehensible to voters.

We believe this is an essential investment in democratic resilience. But it needs to be proactive, not reactive. By the time the doubt takes hold, it’s already too late.

Just as crucially, we are convinced that it’s time to rethink the very nature of cyber threats. People often imagine them in military terms. But that framework misses the true power of these threats. The danger of cyberattacks is not only that they can destroy infrastructure or steal classified secrets, but that they chip away at societal cohesion, sow anxiety and fray citizens’ confidence in democratic institutions. These attacks erode the very idea of truth itself by making people doubt that anything can be trusted.

If trust is the target, then we believe that elected officials should start to treat trust as a national asset: something to be built, renewed and defended. Because in the end, elections aren’t just about votes being counted – they’re about people believing that those votes count.

And in that belief lies the true firewall of democracy.

This article is republished from The Conversation under a Creative Commons license. Read the original article.

New technologies usually follow the technology adoption life cycle. Innovators and early adopters rush to embrace new technologies, while laggards and skeptics jump in much later.

At first glance, it looks like artificial intelligence is following the same pattern, but a new crop of studies suggests that AI might follow a different course – one with significant implications for business, education and society.

This general phenomenon has often been described as “AI hesitancy” or “AI reluctance.” The typical adoption curve assumes a person who is hesitant or reluctant to embrace a technology will eventually do so anyway. This pattern has repeated over and over – why would AI be any different?

Emerging research on the reasons behind AI hesitancy, however, suggests there are different dynamics at play that might alter the traditional adoption cycle. For example, a recent study found that while some causes of this hesitation closely mirror those regarding previous technologies, others are unique to AI.

In many ways, as someone who closely watches the spread of AI, there may be a better analogy: veganism.

AI Veganism

The idea of an AI vegan is someone who abstains from using AI, the same way a vegan is someone who abstains from eating products derived from animals. Generally, the reasons people choose veganism do not fade automatically over time. They might be reasons that can be addressed, but they’re not just about getting more comfortable eating animals and animal products. That’s why the analogy in the case of AI is appealing.

Unlike many other technologies, it’s important not to assume that skeptics and laggards will eventually become adopters. Many of those refusing to embrace AI actually fit the traditional archetype of an early adopter. The study on AI hesitation focused on college students who are often among the first demographics to adopt new technologies.

There is some historical precedent for this analogy. Under the hood, AI is just a set of algorithms. Algorithmic aversion is a well-known phenomenon where humans are biased against algorithmic decision-making – even if it is shown to be more effective. For example, people prefer dating advice from humans over advice from algorithms, even when the algorithms perform better.

But the analogy to veganism applies in other ways, providing insights into what to expect in the future. In fact, studies show that three of the main reasons people choose veganism each have a parallel in AI avoidance.

Ethical Concerns

One motivation for veganism is concern over the ethical sourcing of animal by-products. Similarly, studies have found that when users are aware that many content creators did not knowingly opt into letting their work be used to train AI, they are more likely to avoid using AI.

These concerns were at the center of the Writers Guild of America and Screen Actors Guild-American Federation of Television and Radio Artists strikes in 2023, where the two unions argued for legal protections against companies using creatives’ works to train AI without consent or compensation. While some creators may be protected by such trade agreements, lots of models are instead trained on the work of amateur, independent or freelance creators without these systematic protections.

Environmental Concerns

A second motivation for veganism is concern over the environmental impacts of intensive animal agriculture, from deforestation to methane production. Research has shown that the computing resources needed to support AI are growing exponentially, dramatically increasing demand for electricity and water, and that efficiency improvements are unlikely to lower the overall power usage due to a rebound effect, which is when efficiency gains spur new technologies that consume more energy.

One preliminary study found that increasing users’ awareness of the power demands of AI can affect how they use these systems. Another survey found that concern about water usage to cool AI systems was a factor in students’ refusal to use the technology at Cambridge University.

Personal Wellness

A third motivation for veganism is concern for possible negative health effects of eating animals and animal products. A potential parallel concern could be at work in AI veganism.

A Microsoft Research study found that people who were more confident in using generative AI showed diminished critical thinking. The 2025 Cambridge University survey found some students avoiding AI out of concern that using it could make them lazy.

It is not hard to imagine that the possible negative mental health effects of using AI could drive some AI abstinence in the same way the possible negative physical health effects of an omnivorous diet may drive some to veganism.

How Society Reacts

Veganism has led to a dedicated industry catering to that diet. Some restaurants feature vegan entrees. Some manufacturers specialize in vegan foods. Could it be the case that some companies will try to use the absence of AI as a selling point for their products and services?

If so, it would be similar to how companies such as DuckDuckGo and the Mozilla Foundation provide alternative search engines and web browsers with enhanced privacy as their main feature.

There are few vegans compared to nonvegans in the U.S. Estimates range as high as 4% of the population. But the persistence of veganism has enabled a niche market to serve them. Time will tell if AI veganism takes hold.

This article is republished from The Conversation under a Creative Commons license. Read the original article.

Now in its second year of supporting the College of Computing, the Squarepoint Foundation continues to expand opportunities, enabling students to focus fully on their studies and pursue activities outside the classroom.  

A selection committee led by Mary Hudachek-Buswell, interim chair of the School of Computing Instruction (SCI), chose this year’s cohort.  

“These students exemplify the curiosity, talent, and determination we strive to cultivate in computer science,” Hudachek-Buswell said. “The Squarepoint Foundation Scholarships will give them the opportunity to focus fully on their studies while pursuing research and projects that have the potential to make a real-world impact.” 

The scholars have demonstrated strong leadership across campus, with all five serving as teaching assistants (TAs) and earning faculty honors. The cohort is also engaged in research and study abroad opportunities. 

Founded in 2021, the Squarepoint Foundation supports STEM education and research while partnering with organizations worldwide to expand opportunity and access.  

“We are proud to continue our partnership with Georgia Tech, as we extend our support to a number of students working towards achieving their academic goals,” said Allison Henry, Squarepoint Foundation manager.  

“The Squarepoint Foundation aims to increase access to education, ensuring that all individuals have the opportunity to pursue the degree of their choice, no matter their circumstances. We wish these talented students the best of luck as they undertake their studies and recognize them for their hard work and dedication to the STEM field."

Meet the Scholars

Maria Cymbalyuk 

Cymbalyuk studies Cybersecurity and Information Internetwork threads, focusing on how technical systems shape who is protected or exposed in digital environments. She’s interested in supporting public defenders and improving access to justice through technology. 

“This scholarship made this semester feel less financially stressful and more like I can focus on building the skills and experiences I care about,” Cymbalyuk said. “I want to use my skills to build tools and do research that supports public interest organizations.” 

Marziah Islam 

Zachary Axel is a great example. Reaching well beyond Georgia Tech faculty, he started sending “cold call” emails in 2023 to A.M. Turing Award winners and other computing luminaries.

The emails shared Axel’s vision for a virtual platform that would enable Georgia Tech students and faculty to connect with some of the most distinguished minds in computing. 

The first to accept was Moshe Vardi, a distinguished professor of computer science at Rice University and recipient of the 2020 AAAI Allen Newell Award and several other ACM awards. Vardi’s January 2024 presentation was a hit and served as a template for what grew to become the Turing Mind Series at Georgia Tech.

Three years and nearly two dozen emails later, the series is wrapping up later this month, hosting its 22nd event and its 15th Turing Award winner.

Registration is open for the final session of the Turing Mind Series on March 30, featuring 2019 Turing Laureate Patrick Hanrahan, widely renowned for his enduring contributions to 3D computer graphics.

“There are approximately 70-75 living Turing Award winners. I am proud to say that we have hosted roughly 20% of them for the Turing Minds Series,” said Axel, a former Online Master of Science in Computer Science (OMSCS) student.

“Fifteen felt like the right number to end on. We set out to connect Georgia Tech students and researchers with Turing Laureates, and we did exactly that. Mission accomplished."

As one might guess, Turing Award winners don’t receive a lot of unsolicited emails from students. Vinton Cerf, a 2004 Turing Award winner, says people typically hesitate to engage without some form of endorsement or introduction.

“What is notable about Zachary’s initiative is that he undertook to ‘cold call,’ well, ‘cold email,’ Turing Award recipients to ask them to participate in the program,” said Cerf, who, along with fellow 2004 Turing Laureate Robert Kahn, was instrumental in the pioneering development of fundamental internet communication protocols.

“It is a measure of his confidence and optimism that he succeeded in persuading Turing awardees to engage in the speaking program. Zachary did not hesitate and, in some ways, that may be why he was so successful,” said Cerf.

Axel credits GT Computing Dean Emeritus Zvi Galil with encouraging him and offering guidance along the way.

“Zach is amazing, and he has a lot of chutzpah,” said Galil. “The Turing Minds Series is a remarkable achievement and has become the premier global speaker platform for computer science luminaries.”

Axel thinks he was successful early on for two reasons: he kept it simple, and he used his Georgia Tech email address. He emailed the first five Turing Laureates from the perspective of a student hungry for knowledge.

“I simply asked the Laureates I reached if they would give 30 minutes of their time to virtually present to me and my GT classmates,” said Axel.

He says he would thoroughly research each winner so he could reference a presentation, paper, or another specific aspect of their work in his email. “I did my homework. I made it very easy for them to say yes.”

Axel’s request emails also offered the Turing Laureates –and the Nobel Prize Laureates who were also invited– the option of sharing a presentation or participating in a Q&A. It was this decision to offer a Q&A format that led to one of the most significant moments of the Turing Mind Series for Axel.

“That's how we got legendary 1974 Turing Laureate Donald Knuth. Known for being extremely selective in accepting speaking invitations, he specifically stated that the offer to do a Q&A format was the reason he accepted,” said Axel.

“I also don't think it hurt that the email was coming from an @gatech.edu address, as the Georgia Tech name offered us significant credibility.”

Knuth, widely regarded as the “father of algorithm analysis,” and renowned for his foundational work, The Art of Computer Programming, joined the Turing Minds Series in October 2025 as its 12th guest.

“Thanks so much to you and Parsa for honoring me with an invitation to speak in the online ‘Turing Minds’ series at Georgia Tech,” Knuth said in a note written to Axel.

“It was lots of fun for me this morning to try to answer the excellent questions posed by so many of the viewers.”

Parsa Khazaeepoul is also a former OMSCS student and the co-founder of the series. Axel says that Khazaeepoul’s technical expertise led to the success of the series’ virtual platform.

“Parsa built the series website and managed all of the challenges of hosting and scaling a platform that has impacted to date 4,000+ students and faculty from Georgia Tech and throughout the world.”

The Turing Minds Series at Georgia Tech hosted its first speaker in January 2024. The final installment is scheduled for March 30 at 1 p.m.

But this isn’t the end of the series. Live video recordings of each of the soon-to-be 15 events in the series are available at https://www.turing.rsvp/.

Beyond the website, Axel says the Turing Minds Series is partnering with the ACM, the creators and distributors of the A.M. Turing Award. The goal is to integrate the series into the ACM ecosystem, where it will be accessible to the ACM’s 110,000 student and professional members in more than 170 countries.

"We had a lot of people reach out to us to thank us for what we were doing. Knowing that students left these conversations seeing what's possible in computer science, that meant everything to us," said Axel.

In an article for The Conversation, Georgia Tech international relations scholar and former U.S. Navy intelligence officer Jon Lindsay says that success or failure in war usually depends not on machines but the people who use them. 

Gerald Keys, chief of production for Chris "Ludacris" Bridges’ media company, Karma's World LLC, will be on campus April 14 as part of Georgia Tech’s CTRL+CM Speaker Series.

The event is one of three in the series scheduled this spring. The series will bring together students, faculty, alumni, and industry professionals from Georgia Tech and the Atlanta region to explore the evolving creative technology landscape. Events are scheduled for March 11, March 31, and April 14.

The CTRL + CM Speaker Series, developed by Georgia Tech’s Collective Impact of Creative Technology (CICT), is open to all. The events are free, but registration is required. Registration links for each event are included below.

“The series was created with students in computational media, digital media, and human-computer interaction programs in mind,” said Aneesah Allen, an education outreach manager with the College of Computing.

“However, due to its popularity and success, we have expanded the audience for the speaker series to include the broader Georgia Tech community, students from other Atlanta-area colleges, and anyone interested in creative technology.”

Designed to help students take greater control of their academic and professional paths, the CTRL+CM Speaker Series exposes attendees to career fields on the creative side of technology. Each event will feature a moderated panel discussion with industry leaders, alumni, and faculty, followed by networking opportunities.

Topics will span emerging tools and workflows, creative practice, professional development, and ethical considerations surrounding AI, generative media, and other emerging technologies.

The spring CTRL + CM Speaker Series lineup includes:

• Code That Creates: AI, Generative Media, and the Future of Creative Practice will take place on March 11, from 11 a.m. to 1 p.m. at Coda at Tech Square, 9th Floor Atrium. The discussion will explore how creative coding and generative systems are reshaping artistic practice and the ethical responsibilities of AI-driven creative work.
  • Featured panelists include Mark Riedl, Elizabeth Strickler, Jelani Liddell, and Judith Uchidiuno. Moderated by Bryan Cox.
  • RSVP link: https://forms.office.com/r/zGMYdqUemZ
• Worlds in Motion: Exploring Interactive Media and Emerging Technologies is scheduled for March 31, from 11 a.m. to 1 p.m., in the Price Gilbert Library’s Scholars Event Theater. Panelists will examine developments in augmented, virtual, and extended reality technologies, immersive storytelling, and interactive systems, and how these developments are impacting design and research.
  • Featured panelists: Alison Valk, Kelly Williams, and Meryem Yilmaz Soylu
  • RSVP link: https://forms.office.com/r/Cdp0vxG22u
• Composing with Technology: Digital Tools, Interactive Sound, and Creative Expression will be held on April 14, from 11 a.m. to 1 p.m., also at the Price Gilbert Library. The session will focus on digital audio tools, interactive sound, and innovative approaches to composition and storytelling across games, film, and immersive media.
  • Featured panelist: Gerald Keys, chief of production for Chris "Ludacris" Bridges media company, Karma's World LLC
  • RSVP link: https://forms.office.com/r/exLGwYMTgF

CICT draws on expertise from the College of Computing, the College of Design, and the Ivan Allen College of Liberal Arts. The collective is housed in the Constellations Center for Education in Computing, which has worked since 2017 to expand access to computing education through research, advocacy, and community building.

Georgia Tech researchers say HPC and artificial intelligence (AI) advances this year are poised to improve how people power their homes, design safer buildings, and travel through cities.

According to Qi Tang, scientists will take progressive steps toward cleaner, sustainable energy through nuclear fusion in 2026. 

“I am very hopeful about the role of advanced computing and AI in making fusion a clean energy source,” said Tang, an assistant professor in the School of Computational Science and Engineering (CSE). 

“Fusion systems involve many interconnected processes happening across different scales. Modern simulations, combined with data-driven methods, allow us to bring these pieces together into a unified picture.”

Tang’s research connects HPC and machine learning with fusion energy and plasma physics. This year, Tang is continuing work on large-scale nuclear fusion models.

Only a few experimental fusion reactors exist worldwide compared to more than 400 nuclear fission reactors. Tang’s work supports a broader effort to turn fusion from a promising idea into a practical energy source.

Nuclear fusion occurs in plasma, the fourth state of matter, where gas is heated to millions of degrees. In this extreme state, electrons are stripped from atoms, creating a hot soup of fast-moving ions and free electrons. In plasma, hydrogen atoms overcome their natural electrical repulsion, collide, and fuse together. This releases energy that can power cities and homes.

Computers interpret extreme temperatures, densities, pressures, and plasma particle motion as massive datasets. Tang works to assimilate these data types from computer models and real-world experiments.

To do this, he and other researchers rely on machine learning approaches to analyze data across models and experiments more quickly and to produce more accurate predictions. Over time, this will allow scientists to test and improve fusion reactor designs toward commercial use. 

Beyond energy and nuclear engineering, Umar Khayaz sees broader impacts for HPC in 2026.

“HPC is the need of the day in every field of engineering sciences, physics, biology, and economics,” said Khayaz, a CSE Ph.D. student in the School of Civil and Environmental Engineering. 

“HPC is important enough to say that we need to employ resources to also solve social problems.”

Khayaz studies dynamic fracture and phase-field modeling. These areas explore how materials break under sudden, rapid loads. 

Like nuclear fusion, Khayaz says dynamic fracture problems are complex and data-intensive. In 2026, he expects to see more computing resources and computational capabilities devoted to understanding these problems and other emerging civil engineering challenges.

CSE Ph.D. student Yiqiao (Ahren) Jin sees a similar relationship between infrastructure and self-driving vehicles. He believes AI will innovate this area in 2026.

At Georgia Tech, Jin develops efficient multimodal AI systems. An autonomous vehicle is a multimodal system that uses camera video, laser sensors, language instructions, and other inputs to navigate city streets under changing scenarios like traffic and weather patterns.

Jin says multimodal research will move beyond performance benchmarks this year. This shift will lead to computer systems that can reason despite uncertainty and explain their decisions. In result, engineers will redefine how they evaluate and deploy autonomous systems in safety-critical settings.

“Many foundational problems in perception, multimodal reasoning, and agent coordination are being actively addressed in 2026. These advances enable a transition from isolated autonomous systems to safer, coordinated autonomous vehicle fleets,” Jin said. 

“As these systems scale, they have the potential to fundamentally improve transportation safety and efficiency.”

“It was the era of look left and look right, and one of you will not be here at graduation,” Craig said.

Craig worked hard and graduated with his computer science (CS) bachelor’s degree in 2000, just as the dot-com bubble burst. He returned to Georgia Tech about a year later and has been here ever since.

Craig is the enterprise cybersecurity architect in the Office of Information Technology and has spent nearly three decades at Tech as a student, employee, and instructor.

Along the way, he has earned three degrees from the Institute and helped shape how Georgia Tech approaches cybersecurity in an increasingly complex digital landscape.

Craig began his career at Tech supporting student registration and other core IT systems. He moved fully into cybersecurity about 15 years ago. His technical background was strong, but he saw a gap in his experience.

“I had a lot of technical background and work experience, but not much policy experience,” he said.

Craig enrolled in Georgia Tech’s Master of Science in Information Security to fill in this gap. He said his decision to enroll in the policy track was intentional.

“If you’ve been doing the technical work for 10 years, a technical master’s helps some,” Craig said. “But it is much more useful to study the areas you do not already know well.”

Craig moved into management as his GT career progressed. This path led him once again to the classroom. This time, he pursued an MBA from Georgia Tech’s Scheller College of Business.

Craig believes the combination of cybersecurity and business education is increasingly important for leaders and others.

“There is a big gap in the industry,” he said. “You need people who understand cybersecurity and the business side, and people in business leadership who understand cybersecurity risk.”

Craig is an instructor in the online Master of Science in Cybersecurity program. He teaches incident response and often sees this gap among his students.

“Many business professionals do not know how to respond to a cybersecurity incident,” Craig said. “They are not trained in it. At the same time, many cybersecurity professionals are learning business impacts on the job.”

Craig said business knowledge is essential for aspiring chief information security officers.

“At that level, understanding how cybersecurity supports business goals is more important than deep technical detail,” he said. “You still need the basics, but you also need to talk to the CFO.”

At Georgia Tech, Craig focuses on cybersecurity architecture. His work centers on the design and protection of enterprise systems.

“For example, student information systems have a design,” he said. “We look at how firewalls and other controls fit into that design to protect the data.”

His role continues to evolve as the Institute’s cybersecurity needs change. That evolution mirrors the field itself, especially with the rise of artificial intelligence (AI).

“AI has impacted cybersecurity for longer than people want to admit,” Craig said. “Understanding what is unusual is a big part of security, and AI can be very good at that. It can also be very good at avoiding detection.”

Craig said AI introduces new architectural risks, particularly around data privacy. Tools that analyze student or employee data must be carefully designed to prevent sensitive information from leaking through training or outputs.

“You have to understand the inputs and outputs,” he said. “Otherwise, you can accidentally release data you really care about.”

Privacy has been a recurring theme throughout Craig’s career. He credits courses such as the privacy policy class taught by Professor Peter Swire, the J.Z. Liang Chair in the School of Cybersecurity and Privacy, with shaping his thinking.

“So much of security is about personal data,” Craig said. “Understanding what actually makes data anonymous or not is critical.”

Craig believes that privacy protection depends on training and system design within an institution as large and decentralized as Georgia Tech.

“Training can only get you so far,” Craig said. “People make mistakes. Strong processes limit exposure even when human error happens.”

Looking back, Craig describes his time at Georgia Tech as one of constant growth.

“The industry has massively changed,” he said. “What you learn becomes outdated quickly. You have to keep growing.”

From undergraduate student to cybersecurity leader, Craig’s career reflects both the evolution of Georgia Tech and the fast-changing world of cybersecurity. For him, the learning never stops.

Nearly two dozen venture capital (VC) leaders based in Atlanta and the Southeast participated in a half-day summit at the College on Jan. 21.

Co-hosts Dean of Computing Vivek Sarkar and Noro-Moseley Partners General Partner Alan Taetle organized the invitation-only summit. Their goals were to:

• Showcase the College’s research strengths and entrepreneurial culture
• Deepen connections between academic innovation and startups
• Explore opportunities for collaboration, commercialization, and startup growth

The summit’s guest list included founders, partners, and leaders from VC firms. Many of these firms focus on early-stage startups in SaaS, fintech, cybersecurity, and other emerging technology markets.

Research With Commercial Impact

Sarkar outlined the College of Computing’s academic mission and research priorities during his opening remarks. He emphasized the College’s role in advancing innovation in cybersecurity, artificial intelligence (AI), and other emerging research areas.

“One of the College’s strategic pillars is what I call ‘X to the power of Computing’,” Sarkar said. “Look at any discipline or industry X to see where they're innovating and where their advances are being made, and that’s where Computing meets that discipline.”

Along with remarks from the dean, the summit featured presentations highlighting Georgia Tech’s entrepreneurial ecosystem and College-led research initiatives with strong commercialization potential.

Expanding Support for Student Founders

Jen Whitlow leads Community Partnerships at Fusen, a global platform for student founders created by Atlanta philanthropist Christopher W. Klaus. She described Klaus’s support for student entrepreneurship, including GT Computing’s annual Klaus Startup Challenge. In 2025, Klaus awarded five winning teams $150,000 each to cover startup costs.

Whitlow also updated guests on Klaus’s commitment, announced in May 2025, to covering the incorporation costs for any graduating student who aspires to launch a startup.

“More than 600 graduates from last year’s Spring and Fall Commencements have accepted the gift, and more than 225 recent graduates have completed their incorporation to date,” Whitlow said. She added that a second cohort of Fall 2025 graduates is being processed over the next few weeks.

Offering an enterprise-level view, CREATE-X Rahul Saxena presented recent updates to commercialization at Georgia Tech and efforts to streamline entrepreneurial processes.

Saxena emphasized the launch of Velocity Startups, an accelerator that provides the resources and infrastructure student startups need to bring their innovations to market.

Building the Pipeline From Research to Startup

Following these updates, GT Computing faculty delivered lightning-round presentations highlighting the College’s research strengths in AI, cybersecurity, and high-performance computing.

“The tighter the local investing community is with Georgia Tech, the better off both are,” said Taetle, who has been a member of the College’s Advisory Board for more than 20 years.

“It’s critical in this super-competitive world that we do everything that we can to support this fantastic university.”

Taetle added that the summit was part of a broader effort to strengthen the College’s entrepreneurial pipeline.

“There are some really big ideas here, which could turn into really big companies,” he said. “We’ve made some great strides on the commercialization front, but we still have that opportunity and challenge in front of us.”

The afternoon concluded with a discussion of next steps and engagement opportunities, led by Sarkar and Jason Zwang, GT Computing’s senior director of development. The discussion focused on research partnership opportunities, startup formation, and student involvement.

Zwang emphasized the importance of investing in Atlanta’s innovation ecosystem, citing the city’s strong fundamentals and pro-growth climate for entrepreneurship.

“This gives us a unique opportunity to start working more closely with the local VC community, and it’s also great for our students,” Zwang said.

Sarkar agreed, saying, “There’s no downside for students to get involved in a startup. It might take off and be a bonanza. If not, the experience makes you a more competitive hire because of the breadth of experience you gain at a startup.”

To foster these opportunities for students, Zwang said that a key priority is to establish earlier, more intentional connections among students, startups, and investors.

“This is a pivotal moment,” he said. “We can determine how to connect students with the VC and startup community earlier and ensure these investors remain involved with the College.”

College leaders said the summit underscored Computing’s commitment to fostering an entrepreneurial culture and to building lasting relationships that can help accelerate the real-world impact of its research beyond the Institute.

“Georgia Tech is a force multiplier for entrepreneurship,” said Sarkar. “We’re here to change the world. We want to inspire a culture of bold, big entrepreneurial thinking, and look forward to the next steps that will follow this VC summit.”

Jennifer Kim and Mark Riedl recently received a $500,000 NSF grant to develop large language models (LLMs) that provide strength-based job coaching for autistic job seekers. 

The two Georgia Tech researchers work with Heather Dicks, a career development advisor in Georgia Tech’s EXCEL program, and other nonprofit organizations to provide job-seeking resources to autistic people.

Dicks said the average job search for people with autism can take three to six months in a good economy. It can take up to 18 months in a bad one. However, the new LLMs from Georgia Tech could help to reduce stress and fast-track these job seekers into employment.

Kim is an assistant professor who specializes in human-computer interaction technology that benefits neurodivergent people. Riedl is a professor and an expert in the development of artificial intelligence (AI) and machine learning technologies.

The team’s goal is to identify job-search pain points and understand how job coaches create better employment prospects for their autistic clients.

“Large-language models have an opportunity to support this kind of work if we can have more data about each different individual strength,” Kim said.

“We want to know what worked for them in specific settings at work, what didn’t work, and what kind of accommodations can better help them. That includes how they should prepare for interviews, how they can better represent their skills, how they can address accommodations they need, and how to write a cover letter. It’s a broad range.”

Dicks has advocated for neurodivergent people and helped them find employment for 20 years. She worked at the Center for the Visually Impaired in Atlanta before coming to Georgia Tech in 2017.

She said most nonprofits that support neurodivergent people offer career development programs and many contract job coaches, but limited coach availability often leads to long waitlists. However, LLMs could fill this availability gap to address the immediate needs of job seekers who may not have access to a job coach.

“These organizations often run at a slow pace, and there’s high turnover,” Dicks said. “An AI tool could get the job seeker quicker support. Maybe they don’t even need to wait on the government system.

“If they’re on a waitlist, it can help the user put together a resume and practice general interview questions. When the job coach is ready to work with them, they’re able to hit the ground running.”

Nailing the Interview

Dicks said the job interview is one of the biggest challenges for people with autism.

“They have trouble picking up on visual and nonverbal cues — the tone of the interview, figuring out the nuances that a question is hinting at,” she said. “They’re not giving the warm and fuzzy vibes that allow them to connect on a personal level.”

That’s why Kim wants the models to reflect a strength-based coaching approach. Strength-based coaching is particularly effective for individuals with autism. Many possess traits that employers value. These include:

• Close attention to detail
• Strong technical proficiency
• Unique problem-solving perspectives

“The issue is that they don’t know how these strengths can be applied in the workplace,” Kim said. “Once they understand this, they can communicate with employers about their strengths and the accommodations employers should provide to the job seeker so they can successfully apply their skills at work.”

Handling Rejection

Still, Kim understands that candidates will need to handle rejection to make it through the search process. She envisions LLMs that help them refocus their energy and regain their confidence after being turned down.

“When you get a lot of rejection emails, it’s easy to feel you’re not good enough,” she said. “Being constantly reminded about your strengths and their prior successes can get them through the stressful job-seeking process.”

Dicks said the models should also be able to provide feedback so that candidates don’t repeat mistakes.

“It can tell them what would’ve been a better answer or a better way to say it,” Dicks said. “It can also encourage them with reminders that you get 100 noes before you get a yes.”

You’re Hired, Now What?

Dicks said the role of a job coach doesn’t end the moment a client is hired. Government-contracted job coaches may work with their clients for up to 90 days after they start a new job to support their transition.

However, she said, sometimes that isn’t enough. Many companies have probationary periods exceeding three months. Autistic individuals may struggle with on-the-job training or communicating what accommodations they need from their new employer. 

These are just a few gaps an AI tool can fill for these individuals after they’re hired.

“I could see these models evolving to being supportive at those critical junctures of the probationary period being over or the one-year job review or the annual evaluation that everyone dreads,” she said.

Dicks has an average caseload of 15 students, whom she assists in landing jobs and internships through the EXCEL program.

EXCEL provides a mentorship program for students with intellectual and developmental disabilities from the time they set foot on campus through graduation and beyond.

For more information and to apply, visit EXCEL’s website.

However, most popular AI-powered chatbots are not trained to recognize when someone is in crisis. LLMs also cannot determine when to refer someone to a human specialist.

New Georgia Tech research projects that address these issues may soon provide people seeking mental health support with safer experiences. 

Google has awarded research grants to three faculty members from the School of Interactive Computing to study artificial intelligence (AI), trust, safety, and security. The grants were among dozens awarded by the company to researchers across the country.

Professor Munmun De Choudhury, Associate Professor Rosa Arriaga, and Associate Professor Alan Ritter are among the recipients of the 2025 Google Academic Research Awards. 

Their projects will explore questions like:

• What harms could occur if people consult LLMs for mental health advice?
• Which groups are most at risk of receiving harmful guidance?
• When should an LLM stop responding and refer someone to a human professional?

De Choudhury and Arriaga will examine how LLMs might harm people seeking mental health care.

De Choudhury’s work focuses on spotting when chatbot conversations go wrong and lead users toward self-harm. She is also studying design changes that could prevent these situations.

Her project, Exiting Harmful Reliance: Identifying Crises & Care Escalation Needs, is in partnership with Angel Hsing-Chi Hwang from the University of Southern California. Together, they will review real and synthetic chat transcripts with clinicians to find language patterns that signal risk.

“A chatbot will always give a response and keep talking to you for however long you want,” De Choudhury said. “That may not be a good thing for someone in crisis. We need to know when the right response is to stop and suggest talking to a human.”

Understanding Risks for Low-Income Users

Arriaga’s project, Dull, Dirty, Dangerous: Investigating Trust of Digital Resources Among Low-SES Mental Health Care Seekers, looks at how LLMs affect people with low socioeconomic status (SES).

Dull, dirty, and dangerous is a phrase used to describe work that is well-suited for robot automation because they are repetitive, physically taxing, or hazardous for humans. Arriaga said she adapted these terms for her research to create a taxonomy of the harms AI can cause to people seeking mental health care.

Arriaga also wants to label the trust factors that chatbots have that attract low-SES users to seek their advice, and how these may differ for adults and adolescents across contexts. 

“We know one of the reasons some users go to LLMs is because they aren’t insured and can’t afford a therapist,” she said. “LLMs are available 24-7. Maybe it doesn’t start as a trust issue. Maybe it starts with availability. 

“Some of these human-AI conversations that result in harmful mental health advice didn’t begin on the topic of mental health. In one case, the person started going to the machine for help with homework.

“Then this relationship evolved into personal matters. Should we constrain the system to limit itself to helping someone with their homework and not wander off that subject into mental health matters?”

Managing Privacy Risks for Social Media

Ritter will use the Google award to advance research on social media privacy tools, including interactive AI agents that help people make more informed decisions about what they share online.

His project, AI Tools to Help Users Make Informed Decisions About Online Information Sharing, focuses on reducing privacy risks in both text and images by identifying when posts reveal more than users intend.

“We’ve been developing methods to assess risks in text, and now we’re extending that work to images,” Ritter said. “People post photos without realizing how easily they can be geolocated by advanced AI systems. A casual selfie near home might contain subtle cues about where you live, like a street sign, that reveal private details.”

The project aims to create AI agents that review content within user posts, flag elements that pose risk, and suggest safer alternatives. Ritter said he wants people to maintain control over their privacy without limiting freedom of expression.

Ritter will deploy advanced reasoning models capable of probabilistic privacy estimation. These systems can infer how identifiable a piece of text might be or how likely an image is to reveal a user’s location.

For images, Ritter and his collaborators will use models that identify geolocatable features, allowing users to edit or hide them before posting.

For more on Ritter’s research, read how an LLM he co-developed protects the privacy of users on social media.

The College of Computing named Professor Rich Vuduc as director of the Center for Scientific Software Engineering (CSSE). The Georgia Tech hub is dedicated to building reliable, high-performance software for scientists.  

Under Vuduc’s leadership, CSSE strives to accelerate the pace and increase the quality of scientific discovery by developing custom software tools and best practices tailored to researchers’ needs.

“There is a reproducibility and reliability problem right now with scientific software,” Vuduc said. “The promise of CSSE is to leverage capabilities shared between Georgia Tech, Schmidt Sciences, and industry experts to address this problem.” 

Issues arise because scientists often need to develop their own software for experiments or data analysis. However, troubleshooting coding issues and other bugs can slow down research.

To assist these scientists, CSSE receives their input to create custom software tools and best practices. The center employs professional software engineers who build and deliver products tailor-made to the needs of researchers at Georgia Tech and broader scientific communities.

Beyond its research focus, CSSE helps Georgia Tech fulfill its educational mission. The center provides students with direct access and exposure to real-world software engineering.

As the center enters its third year, Vuduc wants to better prepare students for employment by enhancing their hands-on experience while learning from CSSE engineers.

To achieve this goal, Vuduc is working to establish a Ph.D. fellowship program in which CSSE engineers mentor students. This program would connect academic inquiry with industry expertise, creating the next generation of dynamic leaders in computational science.  

Vuduc also envisions pairing CSSE with Georgia Tech’s Vertically Integrated Projects (VIP) program. This approach would allow undergraduate students to earn class credit while working with CSSE engineers on large software engineering projects spanning multiple semesters.

“The center gives our students access to something that is very unique to find in a university environment,” Vuduc said. 

“The software engineers in CSSE mostly come from industry. They have over 65 years of combined experience doing real-world software engineering that students can learn from.”

Vuduc is a 2010 recipient of the Gordon Bell Prize and a leading expert in high-performance computing (HPC). He was a finalist for the award in 2020 and 2022.

The Gordon Bell Prize, often referred to as the Nobel Prize in supercomputing due to the scope and magnitude of research it recognizes, celebrates achievement in HPC research and application. 

Vuduc joined Georgia Tech in 2007 as one of the first faculty hired for the new Division of Computational Science and Engineering (CSE). Not a stranger of leading new units, he saw CSE begin offering M.S. and Ph.D. degrees in 2008 and attain school status in 2010.  

Since 2021, Vuduc has served as co-director of the Center for Research into Novel Computing Hierarchies (CRNCH). 

CRNCH is an interdisciplinary research center at Georgia Tech that explores technologies and approaches that will usher the next generation of computing. Areas CRNCH studies include quantum computing, brain-inspired computing, and approximate computing. 

Vuduc will step down as CRNCH co-director to fulfill his role as CSSE director. The College of Computing will lead a search for CRNCH’s next co-director.

“In a sense, the CRNCH to CSSE transition was partly a natural one because one thing that contributes to software challenges is that hardware platforms are also changing and evolving very rapidly,” said Vuduc. 

“People are exploring radically new hardware systems and we will have to write software configured for those too. Centers, like CRNCH and CSSE, strongly position Georgia Tech to lead these endeavors.” 

Alessandro (Alex) Orso, the previous CSSE director, departed Georgia Tech earlier this year to become dean of the University of Georgia’s College of Engineering. Orso and Distinguished Professor Irfan Essa wrote the proposal to bring CSSE to Georgia Tech.

Georgia Tech formed CSSE in 2022 after securing an $11 million grant from Schmidt Sciences. Former Google CEO Eric Schmidt and his spouse, Wendy Schmidt, founded the philanthropic venture that funds science and technology research and talent networking programs. 

Georgia Tech’s CSSE is part of Schmidt Sciences’ Virtual Institute for Scientific Software (VISS) program. This network helps scientists obtain more robust, flexible, scalable open-source software. 

Schmidt Sciences is investing $40 million in VISS over five years at four universities: Georgia Tech, University of Washington, Johns Hopkins University, and University of Cambridge.

CSSE uses the funding to employ a software engineering lead, three senior and two junior software engineers. The Schmidt Sciences grant equips these engineers with computing resources to build scientific software. Along with the director, an advisory board guides the group’s work to meet the point of need for scientists in the field. 

“I am grateful to Schmidt Sciences for their support of CSSE. It aligns with our college’s strategic goals and expertise in scientific software, and I am delighted that Rich has agreed to take on this important role,” said Vivek Sarkar, Dean and John P. Imlay Jr. Chair of Computing.

“I know that Rich is committed to growing CSSE's internal and external visibility and long-term sustainability. I am confident that he will also help further socialize CSSE among internal stakeholders across Georgia Tech.”

Despite their importance, most of what scientists know about proteins only comes from a small sample size. This stands in the way of fully understanding how most proteins work and unlocking their full potential.

Georgia Tech’s Yunan Luo believes artificial intelligence (AI) could fill this knowledge gap. The National Science Foundation agrees. Luo is the recipient of an NSF Faculty Early Career Development (CAREER) award. 

“So much of biology depends on knowing what proteins do, but decades of research have concentrated on a relatively small set of well-studied proteins. This imbalance in scientific attention leads to a distorted view of the biological landscape that quietly shapes our data and our algorithms,” Luo said.

“My group’s goal is to build machine learning (ML) models that actively close this gap by generating trustworthy function predictions for the many proteins that remain understudied.”

[Related: Yunan Luo to use AI for Protein Design and Discovery with Support of $1.8 Million NIH Grant]

In his proposal to NSF, Luo coined this rich-get-richer effect “annotation inequality.” 

One problem of annotation inequality is that it slows progress in disease prognosis, drug discovery, and other critical biomedical areas. It is challenging to innovate the few proteins that scientists already know so much about. 

A cascading effect of annotation inequality is that it diminishes the effectiveness of studying proteins with AI.  

AI methods learn from existing experimental data. Datasets skewed toward well-known proteins propagate and become entrenched in models. Over time, this makes it harder for computers to research understudied proteins. 

“Protein annotation inequality creates an effect analogous to a vast library where 95% of patrons only read the top 5% popular books, leaving the rest of the collection to gather dust,” Luo said.

“This has resulted in knowledge disparities across proteins in current literature and databases, biasing our understanding of protein functions.”

The NSF CAREER award will fund Luo with over $770,000 for the next five years to tackle head-on the problem of protein annotation inequality.

Luo will use the grant to build an accurate, unbiased protein function prediction framework at scale. His project aims to:

• Reveal how annotation inequality affects protein function prediction systems
• Create ML techniques suited for biological data, which is often noisy, incomplete, and imbalanced  
• Integrate data and ML models into a scalable framework to accelerate discoveries involving understudied proteins

More enduring than the ML framework, Luo will leverage the NSF award to support educational and outreach programs. His goal is to groom the next generation of researchers to study other challenges in computational biology, not just the annotation inequality problem.

Luo teaches graduate and undergraduate courses focused on computational biology and ML. Problems and methods developed through the CAREER project can be used as course material in his classes.

Luo also championed collaboration with Georgia Tech’s Center for Education Integrating Science, Mathematics, and Computing (CEISMC) in his proposal. 

Through this partnership, local high school teachers and students would gain access to his data and models. This promotes deeper learning of biology and data science through hands-on experience with real-world tools.  

Luo sees reaching students and the community as a way of paying forward the support he received from Georgia Tech colleagues. 

“I am incredibly grateful for this recognition from the NSF,” said Luo, an assistant professor in the School of Computational Science and Engineering (CSE). 

“This would not have been possible without my students and collaborators, whose hard work laid the groundwork for this proposal.”

Luo praised CSE faculty members B. Aditya Prakash, Xiuwei Zhang, and Chao Zhang for their guidance. All three study machine learning and computational bioscience, two of CSE’s five core research areas. 

Luo also thanked Haesun Park for her support and recommendation for the CAREER award. Park is a Regents’ Professor and the chair of the School of CSE.

Though decorated with awards and appearances in leading journals, Zhang will achieve his greatest accomplishment tonight at McCamish Pavilion. He will join the Class of 2025 in walking across the stage, receiving diplomas, and graduating from Georgia Tech.

Before he “gets out” of Georgia Tech, we interviewed Zhang to learn more about his Ph.D. journey and where his degree will take him next. 

Graduate: Ziqi Zhang

Research Interests: Machine learning, foundational models, cellular mechanisms, single-cell gene sequencing, gene regulatory networks

Education: Ph.D. in Computational Science and Engineering

Faculty Advisor: School of CSE J.Z. Liang Early-Career Associate Professor Xiuwei Zhang

What persuaded you to study at Georgia Tech? 

I chose Georgia Tech because it is one of the top engineering institutions in the United States, known for its strength in machine learning and data science. The university offers exceptional research resources and the opportunity to work with leading scholars in my field. Georgia Tech also has very good research infrastructure. The Coda Building is one of the most well-designed and productive research environments I have experienced. Having access to such a space has been a genuine privilege.

How has working on your CSE degree helped you so far in your career?

Working toward my CSE degree has been instrumental in my career development. As an interdisciplinary program, CSE has equipped me with strong computational skills while also deepening my understanding of key application domains. This breadth of training has opened more opportunities during my job and internship searches. In addition, CSE community events, such as HotCSE, the weekly coffee hour, and faculty recruiting activities, have helped me strengthen my scientific communication skills, which are essential for my long-term career growth.

What research project from Georgia Tech are you most proud of?

My favorite research project was scMoMaT, a matrix tri-factorization algorithm for single-cell data integration. I invested a significant amount of time and effort into this work, iterating on the model many times. I’m very proud that it ultimately evolved into a clean, robust, and elegant algorithm.

What advice would you give someone interested in graduate school?

It is important to find an advisor who is supportive and genuinely invested in your career development. A Ph.D. is not an easy journey, and you will inevitably encounter challenges along the way. Having an advisor who can provide thoughtful guidance and dedicated mentorship is one of the most crucial factors in helping you navigate those difficulties.

What is your most favorite memory from Georgia Tech?

CSE’s new student campus visit day every year was one of my favorite times of the year. It was always fun to meet new people, have good food, and enjoy the beautiful view from the Coda rooftop.

What are your plans after graduation?

I plan to keep working in academia after graduation. I’m on the job hunt, currently applying for positions and preparing for interviews.

Her own financial challenges as a student inspired her to establish a needs-based scholarship supporting first-generation and underrepresented students in the College of Computing. 

Banks shares her story and why she wants to expand opportunity and help future technologists build their own paths forward in the following Q&A.

How did your time at Georgia Tech influence the trajectory that brought you to your current role with CNN?

Imagine millions of people rushing to CNN.com and CNN apps the moment breaking news happens, all while your teams are deploying a major platform update! That is my world. My B.S. in computer science taught me to think in systems and logic, not just write software code.

Today, I lead an organization of 80+ engineers and technical leaders building CNN's news publishing platforms and frameworks. As a VP of Software Engineering, I balance system design, crisis response, organization strategy, and diverse problem-solving all at scale.

It sounds like your team hires many early-career software engineers. What skills or qualities do you look for in new talent, and how do Georgia Tech students stand out?

Academic achievements matter because they demonstrate your technical intellect and prove you can master complex concepts. Georgia Tech students naturally excel in pushing through intellectual challenges and rigorous curricula. What stands out beyond your GPA are curiosity, willingness to learn, ability to collaborate, and resilience. Can you go from abstract ideas to tactical software directions? Can you debug your own thinking? Do you ask great questions to understand risks and uncertainties? How well do you work on project teams? The best technologists I have hired have strong technical fundamentals, the ability to collaborate, and the humility to learn. This self-awareness is invaluable.

You're helping expand internship—and potentially co-op—pipelines in Atlanta, New York, and Ottawa. What opportunities do you hope these pathways will create for students?

During my undergraduate years at Georgia Tech, I worked as an intern and co-op at IBM. Transitioning to full-time at IBM after graduating was significantly easier with this real-world work experience. I was already experienced with shipping "real" code, understanding production systems, and learning how corporate organizations operate. I hope to create the same real impact through new hiring pathways, where early experience across different industries equips students with sufficient real-world experience and career jump-starts.

As a HOPE Scholar who faced challenges with living expenses, how did those experiences shape your perspective on access and affordability in higher education?

I'm incredibly grateful to have been a HOPE Scholar during my undergraduate years at Georgia Tech. The program had just started 2 years prior to my entry, so I knew my tuition, fees, and books were covered for 4+ years as long as I maintained a 3.0 GPA or higher. However, I did not qualify for need-based aid because I came from a middle-class family. I did not have the resources to cover my room and board to live on campus. This taught me the lesson that "access" requires far more than admission. I was fortunate to have supportive parents and income from my internships and co-op experiences. But I can only imagine how much more difficult it is for brilliant students to fill financial gaps each semester. Financial stress doesn't just limit opportunities. It steals focus from learning and creates a "ceiling" for how far you can go academically.

Your existing scholarship fund supports first-generation and underrepresented students. Why is this focus especially meaningful to you?

Underrepresented students often carry what I call an "invisible" weight: how to navigate environments without a clear roadmap on what/who/why/when/how, all while trying to build their own future. During my undergraduate years, I was frequently the only, or one of a few, women and/or people of color in my computer science classes. This same pattern has continued throughout my 25+ year career, especially as I have climbed higher on the tech leadership career ladder. As a VP, I have personally met only 10 or so other black female VPs in technology (ever). I established my scholarship fund at Georgia Tech to help change this narrative for future generations. I want to support underrepresented students in pursuing their dream degree at one of the best schools in this country!

You've made a new commitment—$100K over five years—that will qualify your scholarship for the Invest in the Best match. What inspired you to expand your support at this moment?

I am very grateful that the Invest in the Best Match will help my scholarship fund reach a level where a significant financial impact can be achieved every academic year. I am at a stage in my career where I can accelerate what I wish had existed for me. I am personal proof that only one semester of financial security can change a student's entire trajectory. This commitment is also a huge stepping stone toward my ultimate goal of my scholarship fund reaching the $1 million level in future years, creating sustainable support that outlasts my own contributions and my lifetime. 

When you think about the long-term impact of a $200K need-based endowed scholarship, what outcomes or student stories do you hope to see?

I hope scholarship recipients will graduate and then find rewarding careers or seek entrepreneurship that changes their lives. This is how my personal journey has progressed: I continue to seek life-fulfilling challenges, overcome any hurdles, and fulfill my life's purpose by helping others. I hope they reach a point in their life where they look back with gratitude and choose to pay it forward. I am looking forward to reading their alumni newsletter feature one day, where they announce their new self-named scholarship fund and tell the next generation of students, "Someone invested in me. Now I am investing in you."

Many alumni want to give back but aren't sure where to start. What advice would you offer to donors who want their philanthropy to be meaningful and aligned with their values?

I had the idea of starting a scholarship fund at Georgia Tech for over 10 years. I feared making the financial commitment and kept deferring the decision for years. Finally, in 2021, I decided to reach out and request information on the starting steps. There is flexibility in how to meet the initial commitment, including funding sources and the timeframe. Start with this, then focus on scaling the fund later.

The bigger picture is that you are helping future students with their financial needs and letting them know that a Georgia Tech alum believes in them. This profound impact is far greater than any fears over starting a fund.

Looking ahead, how do you envision partnerships between industry leaders like CNN and academic institutions like Georgia Tech shaping the next generation of computing talent?

The best partnerships treat students as colleagues, not just pipelines of talent. We need stronger two-way connections between academia and industry, where theoretical boundaries merge with real-world opportunities. Take streaming video delivery as a concrete example: millions of simultaneous viewers need to watch a live presidential debate or a live March Madness game on their iPhones. How do you maintain quality when network bandwidth drops during a debate? How do you scale real-time infrastructure when traffic spikes from 10 million viewers to 20 million viewers at one time? How do you personalize video delivery by various factors without introducing latency? The next generation of technologists will greatly benefit from learning to solve these problems while actively earning their degrees.

With a newborn and the world in lockdown, I paused my software engineering career and applied to Georgia Tech’s Master of Science in Computer Science program to continue learning without leaving my baby behind.

My journey became a true test of resilience. I completed assignments late at night after my daughters had fallen asleep. I welcomed my second baby in the middle of the program, balancing late-night feedings with project deadlines and Sunday night submissions. It wasn’t easy, but it was worth every moment.

Today, I graduate with a master’s degree, two beautiful daughters, and overwhelming gratitude for my husband, whose unwavering support made this possible, and for my parents in Bangladesh, whose blessings carried me from afar. I’m proud to be the first in my family to graduate from Georgia Tech.

As I step into the next chapter, I am building my tech startup in Austin, combining my expertise in Industrial Engineering with practical, real-world AI to help businesses evaluate, optimize, and automate their workflows.

As a mom of two balancing family, work, and grad school, earning this degree has been one of the most transformative chapters of my life. To every mother, dreamer, and non-traditional student: you don’t have to do it all at once; you just have to keep going.

Some were still alive, but most of the birds were dead. They were all too easy to find.

“I knew birds hit buildings, but I didn’t know much more about the issue at that time, and I was surprised how easily I just found birds,” Betuel said.

Birds flying into windows aren’t isolated events. Environmentalists estimate between 365 million and one billion birds die each year from colliding with structures in the U.S.  

“That statistic is hard for most people to comprehend,” Betuel said. “When you think about the millions of homes we have and these high-rise buildings, and if each one is killing a few a year, that number can get big pretty quick.”

Betuel is the executive director of Birds Georgia, a nonprofit affiliate of the Audubon network that leads bird conservation efforts in Georgia. For 10 years, volunteers from the organization have combed Atlanta’s streets, collecting bird specimens.

Birds Georgia launched Project Safe Flight in 2015 to reduce bird building-collision mortality through data collection. Through legislation, the group aims to make building construction bird-friendly and reduce light pollution.

Environmentalists who study the issue have ranked Atlanta, which sits squarely on a migration route, as the fourth-most dangerous city for birds during fall migration. It is the ninth-most dangerous city during spring migration.

The number of bird deaths from collisions in Atlanta and across the state remains unknown. However, new data tools developed by student researchers in the College of Computing at Georgia Tech are helping Birds Georgia get a clearer picture of the issue.

“We’ve been working with different folks at Georgia Tech for years now, but it’s really picked up lately,” Betuel said. “There’s a lot of momentum and interest on campus to try to make the city safer for birds.”

Pushing for Policy

Ashley Boone, a Ph.D. student in human-centered computing in Tech’s School of Interactive Computing, has led the student effort to help Birds Georgia organize its data. 

Boone said organizing data and knowing how to use it is critical to spark conversations about adopting legislation.

“We often see a gap between data collection and data advocacy,” she said. “Birds Georgia has done an amazing job of tracking collisions in Atlanta over the last 10 years. My goal is to understand the role technology can play in making data useful for policy change.”

User-interface tools designed by computer science undergraduate students James Kemerait and Ian Wood have ramped up that process. One tool converts data input into visualizations optimized for social media, while another consolidates the data collected by volunteers and external sources.

Boone said the desired legislation would mirror policies implemented by New York City. Those policies require the use of bird-safe materials — like window film with patterned designs that break up reflections — in new buildings and buildings undergoing significant renovations. 

What Can Residents Do?

Residents, whose homes account for about 40% of bird collision deaths in the U.S., can also make an impact.

“Households are an underexamined cause of bird collisions,” Boone said. “We focus on the big buildings because it’s easier to convince one manager of a large building to use bird-safe materials, and it’s easier for a policy to address a commercial building. But the sheer volume of residential buildings in the U.S. has a tremendous impact on the number of collisions.”

Steps that homeowners can take include:

• Buying bird-safe film or making do-it-yourself versions of it to put on windows.
• Placing attractive objects like birdhouses and birdfeeders very close or very far away from windows.
• Turning off lights after 9 p.m. on the busiest migration nights of the year.

Betuel said millions of birds can fly over Atlanta on a single night during migration, and they are attracted to the city lights.

“They’ll come into urban centers and collide with an illuminated building, or maybe they overnight somewhere that isn’t safe,” he said. “The next day, they’re surrounded by glass, and birds don’t understand reflection.”

Residents can visit the Birds Georgia website to sign up for the Lights Out Pledge. Those who sign up will receive a text on the 10 busiest migratory nights of the year, and they will be asked to turn their lights off early.

The tools provided by Georgia Tech gave Birds Georgia insight into the number of bird species affected by collisions — more than 140, according to Betuel.

Betuel said that when the organization reaches an estimate of bird collisions, he hopes the number will raise alarms and turn people’s attention to the ecological impact. 

“All these birds being lost results in fewer birds to eat pest insects, fewer birds to pollinate flowers, fewer birds to disperse seeds — all the ecological functions that we need, that they’re doing in the background that most people aren’t keen to,” he said. “If this decline in bird life continues to happen, at some point, there will be issues with our ecosystems functioning as they always have.”

The Yellow Jacket community swarmed campus for the final time of the fall semester to celebrate Commencement ceremonies held Dec. 11 to 13. Graduates from the School of Computational Science and Engineering (CSE) were among the 7,177 new alumni “getting out” of Tech.     

“We are immensely proud of School of CSE and CSE programs graduates in the Class of 2025,” said Haesun Park, Regents’ Professor and Chair of the School of CSE.

“Our collaborative approach to CSE education has prepared these graduates to attain roles in academia, national labs, industry, government, and beyond, where they will lead the next generation of interdisciplinary research.”

Along with administering its flagship CSE Ph.D. and M.S. CSE programs, the School of CSE offers doctoral degrees in computer science and machine learning. Ph.D. graduates who received their diplomas and doctoral hoods on Dec. 11 at McCamish Pavilion included:

• Grant Bruer (Ph.D. CSE-CSE 2025), advised by School of CSE Professor and Associate Chair Edmond Chow
• Dongjin Choi (Ph.D. CSE-CSE 2025), advised by School of CSE Regents’ Professor and Chair Haesun Park
• Hyungu Choi (Ph.D. CSE-AE 2025), advised by Daniel Guggenheim School of Aerospace Engineering Regents’ Professor Dimitri Mavris
• Maxfield Comstock (Ph.D. CSE-CSE 2025), advised by Elizabeth Cherry, College of Computing Associate Dean for Graduate Education and School of CSE Associate Professor
• Andrew Hornback (Ph.D. CS-CSE 2025), co-advised by School of CSE Assistant Professor Yunan Luo and Wallace H. Coulter Department of Biomedical Engineering Professor May Wang
• Ayush Jain (Ph.D. CSE-MSE 2025), advised by School of Materials Science and Engineering Regents’ Entrepreneur and Professor Rampi Ramprasad
• Anurendra Kumar (Ph.D. CS-CSE 2025), co-advised by School of CSE J.Z. Liang Early Career Associate Professor Xiuwei Zhang and Wallace H. Coulter Department of Biomedical Engineering Professor Saurabh Sinha
• Jiajia Xie (Ph.D. CSE-BME 2025), advised by Wallace H. Coulter Department of Biomedical Engineering Associate Professor Cassie Mitchell
• Yuchen Zhuang (Ph.D. ML-CSE 2025), advised by School of CSE Edenfield Early Career Associate Professor Chao Zhang
• Ziqi Zhang (Ph.D. CSE-CSE 2025), advised by School of CSE J.Z. Liang Early Career Associate Professor Xiuwei Zhang

Seven CSE Ph.D. students completed M.S. degrees this fall and will continue their studies at Georgia Tech. They are:

• Jesus Arias (M.S. CSE-CSE 2025), advised by School of CSE Assistant Professor Spencer Bryngelson
• Isabel Berry (M.S. CSE-CHEM 2025), advised by Regents’ Professor C. David Sherrill, who is jointly appointed with the School of Chemistry and Biochemistry and the School of CSE
• Max Hawkins (M.S. CSE-CSE 2025), co-advised by School of CSE Professor Rich Vuduc and Assistant Professor Spencer Bryngelson
• Xiao Jing (M.S. CSE-AE 2025), advised by Daniel Guggenheim School of Aerospace Engineering Regents’ Professor Dimitri Mavris
• Haoyun Li (M.S. CSE-CSE 2025), advised by Professor Felix Herrmann, who is jointly appointed with the Schools of Earth and Atmospheric Sciences, Electrical and Computer Engineering, and CSE
• Yuan Qiu (M.S. CSE-CSE 2025), advised by School of CSE Assistant Professor Peng Chen
• William Schertzer (M.S. CSE-MSE 2025), advised by School of Materials Science and Engineering Regents’ Entrepreneur and Professor Rampi Ramprasad

Georgia Tech’s CSE graduate program includes 12 schools and departments participating as home units. These home units represent the colleges of Computing, Engineering, and Sciences. This approach facilitates an immersive, interdisciplinary experience in which students study computational approaches within domain fields.

Georgia Tech jointly celebrated master’s graduates at a ceremony on Dec. 13 at Bobby Dodd Stadium. After the Institute celebration, graduates were recognized during ceremonies held by their respective colleges.

Mawutor Kofi Amanfu (M.S. CSE 2025)

Sunyoung An (M.S. CSE 2025)

Nischal Bandi (M.S. CSE 2025)

Elijah Bellamy (M.S. CSE 2025)

Meiwen Bi (M.S. CSE 2025)

Hao-Cheng Chang (M.S. CSE 2025)

Tianyu Chen (M.S. CSE 2025)

Yilong Chen (M.S. CSE 2025)

Zhiyu Chen (M.S. CSE 2025)

Seung Eun Choi (M.S. CSE 2025)

Vinodhini Comandur (M.S. CSE 2025)

Zhiyi Dai (M.S. CSE 2025)

Alejandro Danies-Lopez (M.S. CSE 2025)

Zixing Fan (M.S. CSE 2025)

Stefan Faulkner (M.S. CSE 2025)

Mihiri Fernando (M.S. CSE 2025)

Alexandra Freeman (M.S. CSE 2025)

Yuhan Fu (M.S. CSE 2025)

Jack Ganem (M.S. CSE 2025)

Omar Atef Garib (M.S. CSE 2025)

Martin Graffigna (M.S. CSE 2025)

Bochun Guo (M.S. CSE 2025)

Moyi Guo (M.S. CSE 2025)

Xinyu Guo (M.S. CSE 2025)

Yuqi Han (M.S. CSE 2025)

Tianyang Hu (M.S. CSE 2025)

Mingzheng Huang (M.S. CSE 2025)

Po-Han Huang (M.S. CSE 2025)

Wentao Jiang (M.S. CSE 2025)

Boxiao Jin (M.S. CSE 2025)

William-Michael Johnson (M.S. CSE 2025)

Garyoung Lee (M.S. CSE 2025)

Tzu Jung Lee (M.S. CSE 2025)

Congyan Li (M.S. CSE 2025)

Peiru Li (M.S. CSE 2025)

Yuhan Li (M.S. CSE 2025)

Zhiyun Liang (M.S. CSE 2025)

Yuexi Liao (M.S. CSE 2025)

Chenyu Liu (M.S. CSE 2025)

Honglin Liu (M.S. CSE 2025)

Shuojiang Liu (M.S. CSE 2025)

Xuanzhang Liu (M.S. CSE 2025)

Yue Lu (M.S. CSE 2025)

Fang Lunt (M.S. CSE 2025)

Jinrui Ma (M.S. CSE 2025)

Yu Miao (M.S. CSE 2025)

Hui-Chun Mo (M.S. CSE 2025)

Prajwal Kumar (M.S. CSE 2025)

Kavya Krishnan (M.S. CSE 2025)

Felicity Nielson (M.S. CSE 2025)

Jonathan Perng (M.S. CSE 2025)

Yinzhu Quan (M.S. CSE 2025)

Devanshi Shah (M.S. CSE 2025)

Yuxuan Shen (M.S. CSE 2025)

Steven Stewart (M.S. CSE 2025)

Linjun Su (M.S. CSE 2025)

Jingyun Sun (M.S. CSE 2025)

Abdul Rehman Tariq (M.S. CSE 2025)

Yu Chu Tsai (M.S. CSE 2025)

Xunzhi Wen (M.S. CSE 2025)

Jinghua Weng (M.S. CSE 2025)

Andi Xia (M.S. CSE 2025)

Zihao Xiao (M.S. CSE 2025)

Yunxiang Yan (M.S. CSE 2025)

Ziyuan Ye (M.S. CSE 2025)

Linyuan Yu (M.S. CSE 2025)

Bingqing Zhang (M.S. CSE 2025)

Tiankuo Zhang (M.S. CSE 2025)

Yu Zheng (M.S. CSE 2025)

Boye Zhou (M.S. CSE 2025)

Xinjie Zhu (M.S. CSE 2025)

Zilu Zhu (M.S. CSE 2025)

Ephraim is one of eight Georgia Tech students to receive the IP designation this semester. She is joined by CS major Andrew Wang, who is also graduating this month with the IP designation.

Georgia Tech’s IP designation demonstrates a student’s “strong, intentional commitment to global education,” according to Heidi Fiedler, Georgia Tech’s IP academic manager.

She added that employers and graduate programs see IP as evidence of adaptability, intercultural communication skills, and global perspectives. “It meaningfully differentiates a Georgia Tech degree and highlights a graduate’s readiness to thrive in a global environment," Fiedler said.

Ephraim said that her curiosity about the International Plan began during her second year after switching to CS. She discovered the program while browsing Georgia Tech’s website and liked the idea of a long-term global experience, so she decided to go for it.

The IP program requires students to complete three globally focused courses, be proficient in a non-English language, and spend at least 26 weeks abroad. Ephraim exceeded the requirement by completing three international experiences:

• A study-abroad semester at Georgia Tech-Europe in Metz, France
• A two-month internship in Bengaluru, India
• An exchange semester at the University of Sydney in Australia

Tara Berry is the IP academic coordinator for the College of Computing. She said Ephraim’s diverse experiences studying and working abroad are what set her apart from her peers.

“Amber is unique because she has international experience in studying abroad and interning abroad. This is enough time overseas to truly say she has more experience than the average student at navigating work relationships across international locations and different cultures,” Berry said.

Ephraim traveled to France during the summer of 2023 for her first study abroad experience. She immersed herself in French, which she chose for her IP language requirement. She practiced in everyday interactions and often helped classmates navigate conversations at shops or service counters.

“I became a regular at one Japanese restaurant close to my dorm and would always talk with the workers about my week,” she said in a speech delivered earlier this semester. 

Her next experience, a two-month summer 2024 internship at Infosys India, proved more challenging and transformative.

Working in Bengaluru required adjusting to new cultural expectations around communication and workplace relationships. Ephraim said that she and her coworkers would occasionally misinterpret one another. The experience prompted her to develop strategies—such as sketching diagrams—to confirm understanding.

She also learned to adapt to a more community-oriented work culture, where colleagues openly discuss personal well-being and regularly socialize outside the office. The result, she said, was a stronger ability to navigate multicultural environments and ask precise follow-up questions to prevent miscommunication. 

Ephraim arrived in Sydney in February 2025 for a semester-long study exchange. Building on her previous experiences abroad, she says she was prepared to approach the experience with more independence.

One of her goals in Sydney was to broaden her academic portfolio. So, Ephraim, who graduated from Villa Rica High School in 2021, enrolled in virtual reality (VR) design and cybersecurity courses. She also joined the university’s Sustainability Program, volunteered in a community garden, and participated in a series of talks and tours focused on environmental issues.

The semester, she said, helped her refine her interests in computing and gave her “new hobbies and skills that I never would have thought I would like.” 

Across all three experiences, Ephraim developed stronger interpersonal skills and greater confidence speaking with new people. She attributes this personal growth to being pushed outside her comfort zone.

“I’ve never been super extroverted,” she said. “But I am more comfortable talking to people I haven’t met before. I can strike up a conversation and look people in the eye.” 

These skills, along with the global awareness emphasized by the International Plan, will support her next steps.

After graduation, Ephraim plans to build a portfolio for a career in game development. She hopes to begin creating her first original game soon—an exploratory, short-format project that blends fantasy elements with themes of self-reflection.

“I want to get started on my own passion project as soon as I graduate,” she said. 

Ephraim recommends starting early and approaching each experience intentionally for students considering the International Plan. For those who are unsure of their long-term goals, she believes IP is still a good option.

“Extended time abroad provides perspective that is difficult to gain otherwise. It opens you up to a lot of new opportunities,” she said. “It’s an excellent character-building experience.

“It shows a lot of time, effort, and dedication. I feel very proud to look back on it.”

The College of Computing has created a webpage for students who are interested in the International Plan program or the Global Engagement Certificate.

This scenario becomes more likely for hospitals of all sizes as medical technology advances, adding more devices to constantly growing networks.

With the help of a contract award for up to $12 million from the Advanced Research Projects Agency for Health (ARPA-H) UPGRADE program, a team of researchers led by the School of Cybersecurity and Privacy at Georgia Tech will begin developing an advanced cybersecurity platform to help hospitals proactively identify and fix vulnerabilities in their software, devices, and networks. 

“This is a new area of security research,” said Associate Professor Brendan Saltaformaggio. “We not only have to worry about the cybersecurity aspect, but the physical security as well. Our research must be very accurate to make sure patients are safe from cyberthreats.” 

Starting next month, the team of researchers on the Hospital-Integrated Vulnerability Identification and Proactive Remediation (H-VIPER) project will begin developing a system they are calling the Whole-Hospital Simulation (WHS).

The system maps out the online network for hospitals of all sizes and enables IT teams to test their cyber capabilities before going live. The system can also identify threats, such as missed software updates, and alert the IT department.

“Hospitals have thousands of devices connected to their networks, including medical devices,” said Saltaformaggio. “A hospital like Children’s has a huge attack surface. A smaller hospital might have different challenges, but possible entry points are still there.”

The team has already interviewed IT teams at Children’s Healthcare of Atlanta and Hamilton Health Care System. Their findings have provided them with a better understanding of how to scale the WHS system to meet each hospital’s specific needs.

“Hospitals IT processes are notoriously sensitive to disruption, because essentially any kind of down time for rebooting a system or lack of availability can create chaos in the clinical environment,” said Stoddard Manikin, chief information security officer for Children’s Healthcare of Atlanta.

“Our goal is to create very smooth processes and workflow for our patient facing staff and providers to deliver the best care possible. This research opportunity gives us a chance to develop news ways where we can look at these sensitive medical devices and things on the IT network in a healthcare environment and potentially remediate vulnerabilities without taking them out of service.” 

Saltaformaggio and his colleagues found that, regardless of size, security remains retroactive and not proactive. By leveraging their diverse expertise, the research team will ensure that the H-VIPER project addresses vulnerabilities at every layer of hospital technology, from the network to the hardware. 

The School of Cybersecurity and Privacy will lead this initiative, with faculty from the H-VIPER project also representing the College of Computing, the College of Engineering, the School of Electrical and Computer Engineering, the School of Computer Science, and the Georgia Tech Research Institute, along with support from their Ph.D. students and postdoctoral researchers. 

Around 30 Georgia Tech researchers will partner with Emory University, Children’s Healthcare of Atlanta, Hamilton Health Care System, Tufts University, Iowa State University, and Narf Industries. 

Georgia Tech faculty working on the project are:

• Associate Professor Brendan Saltaformaggio
• Regents’ Professor Wenke Lee
• Professor Taesoo Kim
• Professor Fabian Monrose
• Assistant Professor Frank Li
• Associate Professor Saman Zonouz
• Associate Professor Daniel Genkin
• Research Professor Sukarno Mertoguno
• Senior Research Scientist Trevor Lewis  

That’s usually the only information Brandon Biggs receives from digital maps.

Biggs is a human-centered computing Ph.D. student in Georgia Tech’s School of Interactive Computing. He is almost totally blind due to Leber’s Congenital Amaurosis (LCA), a rare degenerative eye disorder affecting about one in 40,000 people.

Based on his experience, Biggs argues that most digital maps aren’t accessible to people who are blind. Even worse, he said, the needs of the blind are usually overlooked.

“When I started research on maps, I had never viewed a weather, campus, or building map, so I didn’t realize the amount of information maps contain,” Biggs said. “How do you represent shapes, orientation, and layout through audio and translate that into a geographic map?”

To answer these questions, Biggs founded XRNavigation, a company focused on developing accessible digital tools. Its flagship product, Audiom, is a cross-sensory map that people can see and hear through text.

“Sighted people view about 300 maps per year, while blind people view fewer than one,” he said. “Blind people don’t view maps; it’s not part of their lives.

“I want to ensure that for blind users, digital maps are no longer just ‘blank.’  They receive the information they need to know to navigate in this world and become more autonomous.”

Organizations that need to include accessible maps in their digital spaces can integrate Audiom into their website or app. 

Georgia Tech recently became one such organization and used Audiom to introduce the first fully accessible digital campus map.

Professor Bruce Walker advises Biggs in Walker’s Sonification Lab, which designs auditory displays for technologies.

“Brandon has the perfect and unique blend of technical skills, research savvy, innovativeness, lived experience, and never-stop attitude to tackle this problem while impacting and improving many lives,” Walker said.

Defining Accessibility

Biggs said most maps limit accessibility features to turn-by-turn directions, tables, or other kinds of alternative text that disregard spatial information. The ability to communicate spatial information distinguishes Audiom.

“According to Web Content Accessibility Guidelines (WCAG), all non-text content — like maps — must include a text alternative with an equivalent purpose,” Biggs said. “But what does ‘equivalent purpose’ mean for geographic maps?

“We argue that every single map, regardless of what it’s showing, communicates general spatialized information and relationships.”

Audiom also prioritizes the information that’s most important to blind users, including sidewalks and buildings.

“There’s a lot of information blind people just don’t get on maps but desperately need,” he said. “They couldn’t care less about the roads. They might need the road name, but they really need the sidewalks.

“If a blind person made a map, they might not even add the roads. And then they would add in the location of doorways, a critical detail that sighted people completely leave out.”

Biggs’s work is already gaining national recognition. XRNavigation was recently one of three companies selected by the Global Accessibility Awareness Day (GAAD) Foundation for a 2025 Gaady Award, which honors work being done to make digital technologies more accessible.

Past and present winners of Gaady Awards range from tech startups to major brands like T-Mobile.

Biggs will accept the award during a banquet on Thursday in San Francisco.

311 systems allow residents to report potholes, broken fire hydrants, and other municipal issues. In recent years, the use of artificial intelligence (AI) to provide 311 services to community residents has boomed across city and state governments. This includes an artificial virtual assistant (AVA) developed by third-party vendors for the City of Atlanta in 2023.

Through survey data, researchers from Tech’s School of Interactive Computing found that many residents are generally positive about 311 chatbots. In addition to eliminating long wait times over the phone, they also offer residents quick answers to permit applications, waste collection, and other frequently asked questions.

However, the study, which was conducted in Atlanta, indicates that 311 chatbots could be causing residents to feel isolated from public officials and less aware of what’s happening in their community.

Jieyu Zhou, a Ph.D. student in the School of IC, said it doesn’t have to be that way.

Uniting Communities

Zhou and her advisor, Assistant Professor Christopher MacLellan, published a paper at the 2025 ACM Designing Interactive Systems (DIS) Conference that focuses on improving public service chatbot design and amplifying their civic impact. They collaborated with Professor Carl DiSalvo, Associate Professor Lynn Dombrowski, and graduate students Rui Shen and Yue You.

Zhou said 311 chatbots have the potential to be agents that drive community organization and improve quality of life.

“Current chatbots risk isolating users in their own experience,” Zhou said. “In the 311 system, people tend to report their own individual issues but lose a sense of what is happening in their broader community. 

“People are very positive about these tools, but I think there’s an opportunity as we envision what civic chatbots could be. It’s important for us to emphasize that social element — engaging people within the community and connecting them with government representatives, community organizers, and other community members.”

Zhou and MacLellan said 311 chatbots can leave users wondering if others in their communities share their concerns.

“If people are at a town hall meeting, they can get a sense of whether the problems they are experiencing are shared by others,” Zhou said. “We can’t do that with a chatbot. It’s like an isolated room, and we’re trying to open the doors and the windows.”

Adding a Human Touch

In their paper, the researchers note that one of the biggest criticisms of 311 chatbots is they can’t replace interpersonal interaction.

Unlike chatbots, people working in local government offices are likely to:

• Have direct knowledge of issues
• Provide appropriate referrals
• Empathize with the resident’s concerns

MacLellan said residents are likely to grow frustrated with a chatbot when reporting issues that require this level of contextual knowledge.

One person in the researchers’ survey noted that the chatbot they used didn’t understand that their report was about a sidewalk issue, not a street issue.

“Explaining such a situation to a human representative is straightforward,” MacLellan said. “However, when the issue being raised does not fall within any of the categories the chatbot is built to address, it often misinterprets the query and offers information that isn’t helpful.”

The researchers offer some design suggestions that can help chatbots foster community engagement and improve community well-being:

• Escalation. Regarding the sidewalk report, the chatbot did not offer a way to escalate the query to a human who could resolve it. Zhou said that this is a feature that chatbots should have but often lack.
• Transparency. Chatbots could provide details about recent and frequently reported community issues. They should inform users early in the call process about known problems to help avoid an overload of user complaints.
• Education. Chatbots can keep users updated about what’s happening in their communities.
• Collective action. Chatbots can help communities organize and gather ideas to address challenges and solve problems.

“Government agencies may focus mainly on fixing individual issues,” Zhou said, “But recognizing community-level patterns can inspire collective creativity. For example, one participant suggested that if many people report a broken swing at a playground, it could spark an initiative to design a new playground together—going far beyond just fixing it.”

These are just a few examples of things, the researchers argue, that 311 services were originally designed to achieve.

“Communities were already collaborating on identifying and reporting issues,” Zhou said. “These chatbots should reflect the original intentions and collaboration practices of the communities they serve.

“Our research suggests we can increase the positive impact of civic chatbots by including social aspects within the design of the system, connecting people, and building a community view.”

At its event this week in Alberta, Canada, the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (AIIDE) is honoring Professor Mark Riedl. The award also honors University of Utah Professor and Division of Games Chair Michael Young, Riedl’s Ph.D. advisor.

Riedl studied under Young at North Carolina State University.

Their 2005 paper, From Linear Story Generation to Branching Story Graphs, highlighted the challenges of using AI to create interactive gaming narratives in which user actions influence the story’s progression. 

In 2005, computer game systems that supported linear, non-branching games were widely used. Riedl introduced an innovative mathematical formula for interactive stories ranging from choose-your-own-adventure novels to modern computer games.

“We didn’t use the term ‘generative AI’ back then, but I was working on AI for the generation of creative artifacts,” Riedl said. “This was before we had practical deep learning or large language models.

“One of the reasons this paper is still relevant 20 years later is that it didn’t just present a technology, it attempted to provide a framework for solving a grand challenge in AI.”

That challenge is still ongoing, Riedl said. Game designers continue to struggle with balancing story coherence against the amount of narrative control afforded to users.

“When users exercise a high degree of control within the environment, it is likely that their actions will change the state of the world in ways that may interfere with the causal dependencies between actions as intended within a storyline,” Riedl and Young wrote in the paper.

“Narrative mediation makes linear narratives interactive. The question is: Is the expressive power of narrative mediation at least as powerful as the story graph representation?”

AIIDE is being held this week at the University of Alberta in Edmonton, Alberta. Riedl will receive the award on Wednesday.

World foundation models (WFMs) enable physical AI systems to learn and operate within synthetic worlds created by generative artificial intelligence (genAI). For example, these models use predictive capabilities to generate up to 30 seconds of video that accurately reflects the real world.

The new framework, developed by a Georgia Tech researcher, enhances the processing speed of the neural networks that simulate these real-world environments from text, images, or video inputs.

The neural networks that make up the architectures of large language models like ChatGPT and visual models like Sora process contextual information using the “attention mechanism.”

Attention refers to a model’s ability to focus on the most relevant parts of input.

The Neighborhood Attention Extension (NATTEN) allows models that require GPUs or high-performance computing systems to process information and generate outputs more efficiently.

Processing speeds can increase by up to 2.6 times, said Ali Hassani, a Ph.D. student in the School of Interactive Computing and the creator of NATTEN. Hassani is advised by Associate Professor Humphrey Shi.

Hassani is also a research scientist at Nvidia, where he introduced NATTEN to Cosmos — a family of WFMs the company uses to train robots, autonomous vehicles, and other physical AI applications.

“You can map just about anything from a prompt or an image or any combination of frames from an existing video to predict future videos,” Hassani said. “Instead of generating words with an LLM, you’re generating a world.

“Unlike LLMs that generate a single token at a time, these models are compute-heavy. They generate many images — often hundreds of frames at a time — so the models put a lot of work on the GPU. NATTEN lets us decrease some of that work and proportionately accelerate the model.”

Dolby and the College each have laboratories in the Coda building, which promotes collaboration at various levels. The audiovisual technology company supported seven research projects last year, spanning computing systems and AI modeling. The partnership also includes events such as this month’s co-hosted student seminar.

“This partnership has reinforced the importance of taking an interdisciplinary approach to our research,” said Vivek Sarkar, Dean of Computing, who worked in industry for two decades before returning to academia.

“I’d like to see us go even deeper in finding ways to combine faculty from different schools and different research areas to work with one partner.”

[VIDEO: GT Computing Dean Discusses Dolby Deal Details with Senior VP]

Yalong Yang, an assistant professor at Georgia Tech’s School of Interactive Computing, is one of the researchers who received Dolby support last year. He and his lab have been working on creating interactive, immersive versions of stories from the New York Times. 

“We’re particularly interested in the engagement side,” Yang said. “That’s what Dolby’s business is about.” Yang and his collaborators have been showing the immersive stories to test subjects while collecting data on heart rate and eye movement.

These collaborations have resulted in several published papers. The code developed is released as open source, enabling anyone to use it. Meanwhile, Dolby scientists can tailor the code for their own needs. 

“We deliberately look for ambitious, farther-looking projects," said Shriram Revankar, senior vice president of Dolby’s Advanced Technology Group.

[RELATED: Dean's Session Spotlights Industry Role in Preparing Students for Workforce Success]

"These are the risks that academia can take and do well in, because they have constant access to new students and other faculty."

At its core, the partnership is about developing relationships among faculty, students, and Dolby, according to Humphrey Shi.

"The students get experience in solving real-world problems for an international corporation, and Dolby’s researchers expand their knowledge through connecting with Tech faculty," said Shi, an associate professor in interactive computing whose research has also been supported by Dolby.

While some of those users can upgrade to Windows 11, hundreds of millions of devices don’t meet the technical requirements. 

Those users might be wondering what else they can do besides throwing away their current device and buying a new one or risking running outdated software on it.

The tech conglomerate faced backlash from environmental and cybersecurity experts after informing Windows users that it would cease providing updates for Windows 10. 

These experts have warned that rendering hundreds of millions of devices practically useless will worsen the ever-growing problem with electronic waste (e-waste) and leave users who can't upgrade vulnerable to cybersecurity threats.

Researchers from Georgia Tech’s School of Interactive Computing (SIC) and School of Cybersecurity and Privacy (SCP) echo those concerns.

Forcing users to replace their devices means that up to 240 million old devices, according to one analysis, will inevitably end up in landfills.

“The problem of e-waste raises the question of why and how these technologies become obsolete,” said Cindy Lin, a Stephen Fleming Early Career Assistant Professor in SIC. 

Lin studies data structures and environmental governance in Southeast Asia and the U.S.

“Scholarship in human-computer interaction (HCI) on repair reveals that many of these technologies suffer from planned obsolescence,” she said. “This means that companies have designed products with a short lifespan, increasing consumption and waste simultaneously.”

When e-waste is dumped in landfills, the organic materials within devices decompose, producing methane, a potent greenhouse gas. And with every discarded device comes the need to produce new ones. The raw materials of these devices are mined, refined, and processed, consuming enormous amounts of energy through the burning of fossil fuels.

The Problem With Hackers

Though Microsoft said it will continue to provide Windows 10 security updates for one year, users are still being pressured to upgrade. By this time next year, if users still haven’t upgraded to Windows 11, they can expect to become easy targets for cyber criminals.

For example, users could receive phishing emails claiming to be from Microsoft about security updates from hackers pretending to be Microsoft. 

“The cybersecurity implications are very serious because new vulnerabilities of Windows 10 will go unpatched for a large part of the user base of this system,” said Mustaque Ahamad, Regents’ Entrepreneur Professor and interim chair of SCP.

“These users will become targets of hackers and cyber criminals who will be able to exploit these vulnerabilities. This will make these machines more prone to attacks such as ransomware and data exfiltration.”

What Can Users Do?

Buying a new device typically costs around $300 at the low end, while some gaming computers can exceed $2,500. 

Josiah Hester, an associate professor in the School of IC who researches computing and sustainability, said users who want to avoid discarding their devices can install Linux Mint, a free universal operating system.

“I would hope that instead of discarding, people might see this as an opportunity to go into a more open ecosystem like Linux Mint, which was designed for Windows users,” Hester said. 

“So much perfectly good hardware is obsolesced by force, when users are more than willing to give it a second life, either through ending support on the software side, subscription services that require certain versions of an OS, or even building the hardware or low-level functions that reduce the autonomy of device owners.” 

Linux Mint is open source and offers its own suite of software products, including a word processor. It also has a built-in security system. It requires 2GB of RAM, 20GB of disk space, and 1024x768 resolution to operate.

On a systemic level, Lin and Hester said people can support organizations that advocate for right to repair and legislation that protects consumers from planned obsolescence.

“HCI studies of informal economies of improvisation and repair have demonstrated that technologies have a longer lifecycle if we have access to expertise on how to repair them without facing penalties such as copyright violations,” Lin said.

“The ongoing right-to-repair movement in the US shows promise in making technology repairable and, in turn, more sustainable.”

“We used to get about one deepfake a month at the beginning of 2023,” said Vijay Balasubramaniyan (PhD CS 2011), CEO and co-founder of Pindrop Security. “Now we’re seeing seven deep-fake attacks per customer every day.”

Balasubramaniyan founded his business in 2011, based on research he did as a Ph.D. student with his advisor, Mustaque Ahamad. Initially, the focus was on detecting deception in voice calls, with banks being the primary customers.

Then two events happened—first, the pandemic. Suddenly, doing business over the phone became more popular than in-person, and the demand for Pindrop’s services grew in healthcare, retail, and beyond.

Second, generative artificial intelligence. Seemingly overnight, almost anyone could use AI to imitate nearly anyone else.

“That has been by far the biggest tailwind for Pindrop,” Balasubramaniyan said. “Everything requires strong identification and strong security.”

The company built its first deepfake protection product eight years ago and has been building on it ever since.

Pindrop recently raised $100 million from investors to expand its deepfake video detection business. The company’s next product is a system for detecting deepfakes in live video conference meetings. It will allow businesses to avoid the scenario faced by the finance worker in Hong Kong, as well as others.

“Am I hiring the right candidate?” Balasubramaniyan said. “Or is this person I’m interviewing not who they said they are? I was surprised, but that’s our biggest use case.”

Deepfake Detection

How does a machine tell the difference between a real person and a fake, even when a human can’t?

“Humans pattern-match a lot,” Balasubramaniyan said. “We always look for familiarity in a noisy world. It’s easy to fool a human.”

Pindrop’s products don’t look for similarities, though. They hunt for differences. A voice call, for example, provides 16,000 samples per second for the programs to analyze. 

“We’re able to pick up so many variances,” Balasubramaniyan said, “and there are so many places for these generative AI systems to make a mistake.”

Pindrop can not only identify fraudulent voice calls, but also which system was used to create them.

“I’ve been surprised by how fast hackers have started using deepfakes in their operations,” Balasubramaniyan said. He gave the example of a fraud that the companies follow, a man named Williams.

“Williams is a guy out of West Africa,” he said. “For the longest time, he’d employ 12 different people, and all day they would dial for dollars. 

“We started seeing Williams replace each of those 12 people with a large language model combined with a text-to-speech system. Now that AI has full-blown conversations with people, they can’t tell the difference. And the bots don’t sleep – they work 24 hours.”

Roots at Tech

Because Balasubramaniyan’s company grew out of his Ph.D. research, he has remained connected to the GT Computing community. He still regularly talks to faculty, especially Ahamad, who has a stake in Pindrop.

“Vijay’s Ph.D. research was of the highest quality, and the Pindrop paper was published in one of the top-tier security conferences,” said Ahamad, professor and interim chair of the School of Cybersecurity and Privacy.

“However, because of his work experience before coming to Georgia Tech, he also focused on the real-world relevance of his research, which led to the launch of Pindrop Security. He is a great example of impactful research that students conduct in our laboratories.”

Balasubramaniyan says he likes to hire fellow alumni.

“Georgia Tech is a great school for our research teams to hire from,” he said.

He and his wife have also endowed a scholarship at Tech. Both are immigrants, and “we want to help other people who have big dreams and small pockets.”

“A lot of these folks, we talk to them, we tell them what we see in the market, we open our networks to them. We’re very fortunate that Georgia Tech allows us to participate in such a meaningful way.”

He thinks Tech is better at generating great talent than many other programs, precisely because it isn’t in Silicon Valley.

“Because we sit here in the South and Atlanta, the ideas we come up with aren’t the latest fad. They’re rooted in great science or great tech. We’re naturally great thinkers because we aren’t fad-chasers.”

Albert Shaw (CS 2016, MS CS 2017) was among the small group of computer science alumni who lent their expertise to help "reconceptualize" the film for the August 28 premiere of The Wizard of Oz at Sphere.

Following last month’s premiere, Shaw, a senior machine learning researcher with Google, shared his experience and some behind-the-scenes details about what it took to bring Dorothy’s adventures to life in 16K resolution.

Wizard of Oz at the Sphere - what is it in your own words? Why is it a big deal?

The Wizard of Oz was one of the iconic pioneers of Technicolor filmmaking, so it's a bit poetic that we were able to adapt it to the unique Sphere experience.

This project wouldn't have been possible two years ago. To me, it's truly been incredible to see the very cutting edge of technology and artistry come together to create this amazing experience that transports you into the Land of Oz.

What did you contribute to the project directly and/or indirectly? How did it push you professionally, and were there any moments of "wow" or "wonder" that are special to you?

Last year, my teammate at Google, Meera Hahn (Ph.D. CS 2022), and I were working on an out-painting model (an AI-based technique for expanding images beyond their original borders) when our manager, Steven Hickson (Ph.D. CS 2020), told us about a project with The Wizard of Oz. We were all like, "That's crazy! Is it even possible? That resolution is insane!" We didn't think it would all happen or that it was technically possible. It's been a crazy journey to get where we are now.

For my part, Meera and I took the out-painting model we had been developing and specialized it for the film. This involved fine-tuning it on the original movie and characters, plus tackling a lot of new problems, like figuring out how to make something significantly bigger while keeping motion and characters consistent.

[RELATED: Lions, Tigers and Tech—Oh My! Alumni Help Dorothy Debut in Ultra-HD at Sphere]

This project really showed me the huge gap between research and application. It also raised a number of new research questions that we've been exploring. We then worked to scale up the model so a whole team could use it to process the entire movie. We even got to run many of the shots ourselves, from testing to custom workflows for some of the most challenging scenes.

Working directly with the Magnopus creatives in Los Angeles was one of the most amazing experiences I had. We built a great workflow where we'd improve what the artists gave us, and they'd improve our outputs to feed back into the models and repeat the process.

Seeing the scenes I worked on, first on the test Sphere and then on the real Sphere, was jaw-dropping. You can't really understand how big the screen is until you're there in person.

Image

Image courtesy of Google DeepMind

In the back of my mind, I was always thinking, "I really hope this all works out." It wasn't until I saw the first scarecrow scene (my favorite scene in this version) on the full Sphere –after all our back-and-forth iterations, artist touch-ups, and compositing with full CG renders – that I was like, "This is really going to work!" It's incredible what everyone achieved together.

Starting in May, I also gained a broader understanding of the entire process by serving as an ML Tech Lead, supporting other workflows for the Super Resolution and Performance team. I did a lot of debugging, putting out fires, and helping with the final touches on everything in the various tracks, and working with Magnopus to ensure everything fit together.

The work everyone did is truly groundbreaking. Seeing it all come together with the practical effects at the premiere was just sublime. I even got one of the sought-after foam apples!

From a technology/AI standpoint, in lay terms, what stands out to you?

What amazes me is how quickly we were able to enable this and how it wouldn't have been possible if we had started even a year earlier. It's been amazing being in the middle of this revolution in video and other generative models. However, putting it into professional filmmaking at this unprecedented 16k resolution, with the quality and character consistency we achieved, was amazing.

Most base video generation models currently target around 720p, so I'm most proud of the fact that we've been able to accomplish this working together with all the creatives and others on this project.

Stasko achieved a great deal during his 36 years as a professor at Georgia Tech and made significant contributions to data visualization research and innovations. He is a Fellow of the ACM and IEEE and received the IEEE Visualization and Graphics Technical Community Lifetime Achievement Award. 

In all those years, none of his students or colleagues could recall a moment when he didn’t demonstrate kindness.

“He supported me in fleshing out my ideas into a Ph.D. dissertation,” said Dean Jerding (CS Ph.D. 1997), one of Stasko’s former students. “He was always calm and communicated any criticism in a very positive way. He never said I had a dumb idea. He was always encouraging, and he redirected you with his input.”

The School of Interactive Computing bid farewell to Stasko on Thursday, following his official retirement in July. 

During the event, Shaowen Bardzell, School of IC chair and professor, announced the establishment of the John Stasko Award for Teaching Excellence in Stasko’s honor. Bardzell said the award will be given each year to as many as “two faculty members in the School of Interactive Computing whose teaching and mentoring channel John’s passion and care for our students.”

“You can be effective while being nice, and you can be heard while being quiet and thoughtful,” said Keith Edwards, a professor in the School of IC who was one of Stasko’s first students. “He’s the same even-keeled, thoughtful person as he was when I first knew him. He’s very generous. If it hadn’t been for John, I think there’s a chance I would’ve fallen through the cracks when I was looking for an advisor at Georgia Tech. I’m very fortunate he took me on.”

New College, New Blood

Stasko came to Georgia Tech in 1989 fresh off completing his Ph.D. in computer science at Brown University. That was a year before the establishment of the College of Computing at Georgia Tech. The computer science program was administered by the School of Information and Computer Science, which was housed in the College of Sciences.

“It was exciting because we were igniting computer science at Georgia Tech, and there were a lot of young faculty like me who were brand new, right out of college,” Stasko said. “There was this spirit of working together and wanting to make something great here.”

Stasko said when the College of Computing was established in 1990, Georgia Tech ranked outside the top 20 of U.S. News and World Report’s computer science program rankings. 

Many new faculty members like Stasko were interested in data visualization, computer graphics, and human-computer interaction. Georgia Tech quickly bolstered its computer science reputation by positioning itself at the forefront of those emerging fields with the creation of the Graphics, Visualization, and Usability (GVU) Center.

“A lot of the top five to 10 schools like Stanford, MIT, and Berkeley were very strong in the traditional subareas of computer science,” Stasko said. “I think it helped us to develop a strength in HCI, graphics and visualization. We were one of the earliest to embrace those, so it made it easier for us to shine. U.S. News and World Report had a new sub-ranking called Graphics and HCI, and we were ranked No. 1 very early on. That really helped us.”

Growing as a Mentor

Stasko credits Jim Foley, the first director of GVU, who now has a scholarship named in his honor for outstanding graduate students, as the model for how to conduct oneself as a teacher.

“Jim was the most wonderful mentor I could’ve had,” Stasko said. “He was a famous professor, and everyone in computer science around the country knew him, but he was always so humble, and he would meet all the new junior faculty and want to help us get going. He allowed us to shine.”

Stasko became most well-known for his research, particularly for his invention of Jigsaw in 2007. Jigsaw is a visualization algorithm that can create a visual index of a large document collection.

“It could help an analyst see the story that’s spread across 1,500 different documents about a police case, for example,” he said. “Or maybe they were reviews of a product that you wanted to learn about, or which car or which TV you should buy without having to read 1,500 reviews. We used early machine learning methods to analyze the text and created a suite of different visualizations communicating that analysis.”

In addition to his research, Stasko taught an intro to JavaScript course for 20 years to thousands of Tech students. Though it wasn’t required of him to teach it, he said he enjoyed interacting with incoming first-year students because it “helped keep me feeling young.”

In 2007, Stasko joined the faculty of the newly created School of Interactive Computing. He served as the interim chair of the school from 2021 to 2022, and he was also named Regents’ Professor by the University System of Georgia in 2021.

Leaving a Legacy

Today, the College of Computing has the No. 5 undergraduate and No. 6 graduate computer science program in the U.S. and is the largest college on Georgia Tech’s campus.

“I’m not sure any other CS program in the country has had that kind of jump like we have had over the past 35 years,” Stasko said. “The higher you go, the harder it is to jump even one spot.

“I think we knew that (the College) was going to grow and that was part of the plan. I’m not sure I would’ve envisioned we’d ever be 150 to 200 faculty in the college, but we could all see computer science was going to be a crucial part of society going forward.”

Stasko will continue to be a part of the School of IC as Professor Emeritus. His final student, Alexander Bendeck, finishes his Ph.D. in 2026. 

Bendeck will be the 25th student Stasko has advised and graduated over his career. He said he never had the funding to run a large lab, but that allowed him to invest in the students he took under his wing.

“I often found some unconventional Ph.D. students,” Stasko said. “Some of my early students started in very different areas of computer science. I’ve looked for diamonds in the rough. 

“I see some of them now with their families and they make me feel old because they have kids who are in college now. But they’ve done well. I think half of my students have gone into academia, and the other half into industry. I’m very proud in all that they’ve achieved, both personally and professionally.”

The Aarhus Conference, hosted by Aarhus University in Denmark, has been held every decade since 1975, addressing the most urgent and vital issues in computing worldwide. 

The latest conference, titled Computing (X) Crisis, took place in August and featured presentations, critiques, and workshops that explored computing’s influence on the human condition in a world filled with crises.

Assistant Professor Cindy Lin, Associate Professor Lynn Dombrowski, and School of Interactive Computing Professor and Chair Shaowen Bardzell authored the paper Whose, Which, and What Crisis? A Critical Analysis of Crisis in Computing Supply Chains. It was one of only 15 papers selected by conference organizers.

In the paper, in which Lin is credited as the lead author, the researchers advance a theoretical framework for understanding crises that impact the computing supply chain.

Bardzell, who served as program chair of the 2015 Aarhus Conference, approached Dombrowski and Lin about collaborating on a paper submission. Bardzell said the conference gets more than 100 submissions and has a minuscule acceptance rate.

“I knew I was going to go no matter what because I enjoyed it so much 10 years ago,” Bardzell said. “I was fortunate to come together with Lynn and Cindy. We spent six months reading, thinking, and debating together every week, and it was a pleasure to write it together.”

The authors identified common themes in areas they were already researching and examined how these themes affected the computing supply chain.

“We wanted to think about what this word means in relation to computing,” Dombrowski said. “Who gets to take advantage of a crisis, or who can construct a crisis in relation to computing? What’s not being talked about when we use that word?”

Lin is studying the rise of data centers and their impact on the environment and consumers. Dombrowski is an expert on the labor market and unjust labor practices. Bardzell has conducted extensive research on how chip manufacturing affects farming and agriculture in her homeland of Taiwan.

“We don’t often think about computing research as intergenerational colleagues working together,” Lin said. “I feel like the three of us represent very interesting generations of computing research that’s tied to critically thinking about the social and political aspects of computing. Each of us has different ways of thinking about those things.”

In the paper, the three authors discuss the concept of “against crisis thinking,” which emphasizes that crises affecting the computing supply chain aren’t self-evident phenomena. Human-computer interaction scholars, they say, should pay more attention to how the word “crisis” is introduced into public discourse and how it can be exploited by powerful actors and impact marginalized communities.

“Some players get to declare what is a crisis and whom it affects,” Lin said. “They create solutions to resolve the crisis, but they might not address what a chronic experience of a crisis may be.”

Although Bardzell said she considers it an honor to present at a conference that is so selective and is held only once a decade, she was encouraged to be among researchers dedicated to solving pressing societal and planetary issues.

“Academia can appear as a cutthroat environment where you’re trying to establish your brand and be known for XYZ,” Bardzell said. “At Aarhus, there was a strong sense of community and working alongside each other, and we’re better because of the people who work alongside us.”

Lin agreed and said that participating in Aarhus is different from the annual conferences where the researchers normally submit papers. 

“There’s something special about reflecting every 10 years,” Lin said. “It shows how much has changed but also how much things have remained the same.”

Raphaël Pestourie has earned back-to-back selections to the Institute’s Course Instructor Opinion Survey (CIOS) honor roll, placing him among the top-ranked teachers for Fall 2024 and Spring 2025.

By returning to the classroom this semester to teach two more courses, Pestourie continues to leverage proven experience to mentor the next generation of researchers in his field.

“Students played a very important part in the survey process, and I thank them for making the classes great,” said Pestourie, an assistant professor in the School of Computational Science and Engineering (CSE).

“I'm incredibly grateful that students shared their feedback so that I could go the extra mile to not only apply my expertise to teach in ways that I think work, but transform my instruction to reach students in the most impactful way I can.”

CIOS honor rolls recognize instructors for outstanding teaching and educational impact, based on student feedback provided through end-of-course surveys. 

Student praise of Pestourie’s CSE 8803: Scientific Machine Learning class placed him on the Fall 2024 CIOS honor roll. He earned selection to the Spring 2025 honor roll for his instruction of CX 4230: Computer Simulation. 

CSE 8803 is a graduate-level, special topics class that Pestourie created around his field of expertise. Scientific machine learning involves merging two traditionally distinct fields: scientific computing and machine learning.

In scientific computing, researchers build and use models based on established physical laws. Machine learning differs in that it employs data-driven models to find patterns without prior assumptions. Combining the two fields opens new ways to analyze data and solve challenging problems in science and engineering.

Pestourie organized student-focused scientific machine learning symposiums in Fall 2023 and 2024. CSE 8803 students work on projects throughout the course and present their work at these symposiums. Pestourie will use the same approach this semester. 

Compared to CSE 8803, CX 4230 is an undergraduate course that teaches students how to create computer models of complex systems. A complex system has many interacting entities that influence each other’s behaviors and patterns. Disease spread in a human network is one example of a complex system. 

CX 4230 is a required course for computer science students studying the Modeling & Simulation thread. It is also an elective course in the Scientific and Engineering Computing minor.  

“I see 8803 as my educational baby. Being acknowledged for it with a CIOS honor roll felt great,” Pestourie said. 

“In a way, I'm prouder of CX 4230 because it was a large, undergraduate regular offering that I was teaching for the first time. The honor roll selection came almost as a surprise.”

To be eligible for the honor roll recognition, instructors must have a minimum CIOS response rate of 70%. Composite scores for three CIOS items are then used to rank instructors. Those items are:

• Instructor’s respect and concern for students
• Instructor’s level of enthusiasm about the course
• Instructor’s ability to stimulate interest in the subject matter

Georgia Tech’s Center for Teaching and Learning (CTL) and the Office of Academic Effectiveness present the CIOS Honor Rolls. CTL recognizes honor roll recipients at its Celebrating Teaching Day events, held annually in March.

CTL offers the Class of 1969 Teaching Fellowship, in which Pestourie participated in the 2024-2025 cohort. The program aims to broaden perspectives with insight into evidence-based best practices and exposure to new and innovative teaching methods.

The fellowship offers one-on-one consultations with a teaching and learning specialist. Cohorts meet weekly in the fall semester and monthly in the spring semester for instruction seminars. 

The fellowship facilitates peer observations where instructors visit other classrooms, exchange feedback, and learn effective techniques to try in their own classes.

“I'm very grateful for the Class of 1969 fellowship program and to Karen Franklin, who coordinates it,” Pestourie said. “The honor roll is not just a one-person award. Support from the Institute and other people in the program made it happen.”

Like in Fall 2023 and 2024, Pestourie is teaching CSE 8803: Scientific Machine Learning again this semester. Additionally, he teaches CSE 8801: Linear Algebra, Probability, and Statistics.

Linear algebra and applied probability are among the fundamental subjects in modern data science. Like his scientific machine learning class, Pestourie created CSE 8801. This semester marks the second time Pestourie is teaching the course since Fall 2024.

Pestourie designed CSE 8801 as a refresher course for newer graduate students. This addresses a point of need to help students get off to a good start at Georgia Tech. By offering guidance early in their graduate careers, Pestourie’s work in the classroom also aims to cultivate future collaborators and serve his academic community.

“I see teaching as our one shot at making a good first impression as a research field and a community,” he said. 

“I see my work as a teacher as training my future colleagues, and I see it as my duty to our community to do my best in attracting the best talent toward our research field.”

Socrates, widely regarded as the founder of Western philosophy, declared, "I know that I know nothing." This simple statement highlights the wisdom of acknowledging the limits of one's own knowledge.

A simple statement, yes, but like some people, LLMs struggle with saying “I don’t know.” In fact, LLMs often can't admit that they don't know something because of the way they are trained, according to a research team that includes a Georgia Tech computer science (CS) professor.

Pre-training LLMs involves them learning to predict the next word correctly by training on massive datasets of text, images, or other data. Models are evaluated and adjusted based on their performance against standard benchmarks, which are "rewarded" for preferred outputs or answers.

Current evaluation protocols, however, penalize non-responses the same as incorrect answers and do not include an "I don't know" option.

According to CS Professor Santosh Vempala, these pre- and post-training shortcomings are what lead LLMs to provide seemingly plausible but false responses known as hallucinations.

Vempala is a co-author of Why Language Models Hallucinate, a research study from OpenAI and Georgia Tech, released in September. He says that there is a direct correlation between an LLM's hallucination rate and its misclassification rate regarding the validity of a given response.

"This means that if the model can't tell fact from fiction, it will hallucinate," Vempala said. 

"The problem persists in modern post-training methods for alignment, which are based on evaluation benchmarks that penalize 'I don't know' as much as wrong answers."

Because of the penalties for knowing that it knows nothing – to paraphrase Socrates – guessing is a more rewarding option for current LLMs than admitting uncertainty or ignorance.

The research incorporates and builds on prior work from Vempala and Adam Kalai, an OpenAI researcher and lead author of the current paper. Their earlier work found that LLM hallucinations are mathematically unavoidable for arbitrary facts, given current training methodologies. 

"We've been talking about this for about two years. One corollary of our paper is that, for arbitrary facts, despite being trained only on valid data, the hallucination rate is determined by the fraction of missing facts in the training data," said Vempala, Frederick Storey II Chair of Computing and professor in the School of CS.

To illustrate this point, imagine you have a huge Pokémon card collection. Pikachu is so familiar that you can confidently describe its moves and abilities. However, accurately remembering facts about Pikachu Libre, an extremely rare card, would likely be more difficult.

“More to the point, if your collection has a large fraction of unique cards, then it is likely that you are still missing a large fraction of the overall set of cards. This is known as the Good-Turing estimate,” Vempala said.

[OpenAI Blog: Why Language Models Hallucinate]

According to Kalai and Vempala, the same is true for LLMs based on current training protocols.

“Think about country capitals,” Kalai said. “They all appear many times in the training data, so language models don’t tend to hallucinate on those.

“On the other hand, think about the birthdays of people’s pets. When those are mentioned in the training data, it may just be once.

“So, pre-trained language models will hallucinate on those. However, post-training can and should teach the model not to guess randomly on facts like those.”

Vempala thinks tinkering with pre-training methods could be risky because, overall, they work well and deliver accurate results. However, he and his co-authors offered suggestions for reducing the occurrence of hallucinations with changes to the evaluation and post-training process.

Among the team's recommended changes is that more value be placed on the accuracy of an LLM's responses rather than on how comprehensive their responses are. The team also suggests implementing what it refers to as “behavioral calibration.”

Using this methodology, LLMs would only answer if their confidence level exceeds target thresholds. These thresholds would be tuned for different user domains and prompts. They would also appropriately reduce penalties for “I don’t know” responses, along with appropriate expressions of uncertainty and wrong answers.

Vempala believes that implementing some of these modifications could result in LLMs that are trained to be more cautious and truthful. This shift could lead to more intelligent systems in the future that can handle nuanced, real-world conversations more effectively.

"We hope our recommendations will lead to more trustworthy AI," said Vempala. "However, implementing these modifications to how LLMs are currently evaluated will require acceptance and support from AI companies and users."

The GT Computing community recently gathered to celebrate 2025 Hall of Fame inductees Dmitri Alperovitch (CS 2001, MS InfoSec 2003) and Georgia Tech Professor Emeritus Rich LeBlanc.

Alperovitch is the co-founder and chairman of Silverado Policy Accelerator and the bestselling author of World on the Brink: How America Can Beat China in the Race for the 21st Century.

[RELATED: Cybersecurity Pioneer Engages Graduate Students During Campus Visit]

LeBlanc was assistant director of Georgia Tech’s School of Information Science before playing a key role in creating the College of Computing in 1990.

The celebration also honored three prior inductees – Neha Narkhede (CS MS 2007), Professor Emeritus Shamkant Navathe, and Phyllis Schneck (CS PhD 1999) – who were unable to attend previous Hall of Fame induction events.

Vivek Sarkar, John P. Imlay Jr. Dean of Computing at Georgia Tech, welcomed guests and the Hall of Fame inductees to the event, held at downtown Atlanta’s Ventanas on Sept. 19.

“We gather here tonight to celebrate the members of our community whose vision, dedication, and extraordinary efforts have shaped our College into the vibrant, innovative, and entrepreneurial powerhouse it is today,” said Sarkar.

“Through the voices of our honorees tonight, you will learn more about the full breadth and depth of our story, about our College and its people who have had an outsized influence on education, research, industry, community, and more.”

Narkhede is a tech entrepreneur and the founder and CEO of Oscilar. Navathe, who founded GT’s database systems research group, started teaching at the college since its inception.

Schneck (CS PhD 1999) is Vice President and Global Chief Information Security Officer (CISO) for Northrop Grumman. In this role, she oversees the company’s global cybersecurity strategy and policies. In this role, she oversees the company’s global cybersecurity teams, operations, strategy, and policies. She is also a member of the College of Computing’s Advisory Board.

Following the dean’s remarks, Amanda Moore, Computing’s alumni relations director, introduced the 2025 Rising Star Award winners, Stacee Birdsong (CS 2018) and Jennifer Whitlow (CM 2009).

“The College of Computing has a wide range of talented alumni in every age group,” said Moore.

“The Rising Star Award honors the best of our younger alumni, those who have made an outstanding impact in the early parts of their careers.”

Sarkar returned to the podium to introduce and speak briefly about the 2025 Hall of Fame inductees. Alperovitch and LeBlanc each shared their gratitude and remarks from the podium following the dean’s introduction.

Sarkar then introduced and shared remarks about Narkhede, Navathe, and Schneck, members of prior GT Computing Hall of Fame inductee cohorts. Narkhede and Navathe are members of the sixth cohort, inducted in 2024. Schneck was part of the second cohort, inducted in 2020.

Inductee, honoree, and Rising Star biographies are available on the College’s website and linked below.

2025 Hall of Fame Inductees & Honorees

• Dmitri Alperovich (CS 2001, MS InfoSec 2003) – Chairman of Silverado Policy Accelerator; CrowdStrike, Co-founder and Former Chief Technological Officer
• Richard LeBlanc – Professor Emeritus, Georgia Tech & Seattle University
• Neha Narkhede (CS MS 2007) – Hall of Fame class of 2024, Oscilar, Co-founder and CEO
• Shamkant Navathe – Hall of Fame class of 2024, Professor Emeritus, Georgia Tech
• Phyllis Schneck (CS PhD 1999) – Hall of Fame class of 2020, Northrop Grumman, Vice President and Chief Information Security Officer

2025 Rising Stars

• Stacee Birdsong (CS 2018) – Rainforest, Director of Product & Engineering
• Jennifer Whitlow (CM 2009) – Fusen, Head of Community Partnerships

Danfei Xu, an assistant professor in Georgia Tech’s School of Interactive Computing, is introducing new models that provide robots with “on-the-job” training.

The National Science Foundation (NSF) awarded Xu its CAREER award given to early career faculty. The award will enable Xu to expand his research and refine his models, which could accelerate the process of robot deployment and alleviate manufacturers from the burden of achieving perfection.

“The main problem we’re trying to tackle is how to allow robots to learn on the job,” Xu said. “How should it self-improve based on the performance or the new requirements or new user preferences in each home or working environment? You cannot expect a robot manufacturer to program all of that.

“The challenging thing about robotics is that the robot must get feedback from the physical environment. It must try to solve a problem to understand the limits of its abilities so it can decide how to improve its own performance.”

As with humans, Xu views practice as the most effective way for a robot to improve a skill. His models train the robot to identify the point at which it failed in its task performance.

“It identifies that skill and sets up an environment where it can practice,” he said. “If it needs to improve opening a drawer, it will navigate itself to the drawer and practice opening it.”

The models allow the robot to split tasks into smaller parts and evaluate its own skill level using reward functions. Cooking dinner, for example, can be divided into steps like turning on the stove and opening the fridge, which are necessary to achieve the overall goal.

“Planning is a complex problem because you must predict what’s going to happen in the physical world,” Xu said. “We use machine learning techniques that our group has developed over the past two years, using generated models to generate positive futures. They’re very good at modeling long-horizon phenomena.

“The robot knows when it’s failed because there’s a value that tells it how well it performed the task and whether it received its reward. While we don’t know how to tell the robot why it failed, we have ways for it to improve its skills based on that measurement.” 

One of the biggest barriers that keeps many robots from being made available for public use is the pressure on manufacturers to make the robot as close to perfect as possible at deployment. Xu said it’s more practical to accept that robots will have learning gaps that need to be filled and to implement more efficient real-world learning models.

“We work under the pressure of getting everything correct before deployment,” he said. “We need to meet the basic safety requirements, but in terms of competence, it is difficult to get that perfect at deployment. This takes some of the pressure off because it will be able to self-adapt.”

Virtual Workspace for Data Workers

Yalong Yang, another assistant professor in the School of IC, also received the NSF CAREER Award for a research proposal that will design augmented and virtual reality (AR/VR) workspaces for data workers. 

“In 10 years, I envision everyone will use AR/VR in their office, and it will replace their laptop or their monitor,” Yang said.

Yang said he is also working with Google on the project and using Google Gemini to bring conventional applications to immersive space, with data tools being the most complicated systems to re-design for immersive environments.

The immersive workspace and interface will also enable teams of data workers to collaborate and share their data in real-time.

“I want to support the end-to-end process,” Yang said. “We have visualization tools for data, but it’s not enough. Data science is a pipeline — from collecting data to processing, visualizing, modeling and then communicating. If you only support one, people will need to switch to other platforms for the other steps.”

Yang also noted that prior research has shown that VR can enhance cognitive abilities, such as memory and attention and support multitasking. The results of his project could lead to maximizing worker efficiency without them feeling strained.

“We all have a cognitive limit in our working memory. Using AR/VR can increase those limits and process more information. We can expand people’s spatial ability to help them build a better mental model of the data presented to them.”

Yang was also recently named a 2025 Google Research Scholar as he seeks to build a new artificial intelligence (AI) tool that converts mobile apps into 3D immersive environments.