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.”

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 alumnus Zijie (Jay) Wang 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 approaches of over a dozen quantum computing companies are now being evaluated through the Quantum Benchmarking Initiative (QBI), a project of the U.S. Defense Advanced Research Projects Agency (DARPA). According to the agency, QBI “aims to rigorously verify and validate whether any quantum computing approach can achieve utility-scale operation – meaning its computational value exceeds its cost – by the year 2033.”
 

Supporting the effort, a 40-person interdisciplinary research team from the Georgia Tech Research Institute (GTRI) has joined the test and evaluation component of QBI, providing unbiased subject-matter experts to work with 13 other research organizations in evaluating the R&D plans of participating quantum computer companies. Through this collaboration, the GTRI team is working with more than 400 other third-party experts on the project.
 

Read the complete article on the GTRI news site

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.”

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. 

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

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.

The Department of Energy Office of Science recently released two reports through its Advanced Scientific Computing Research (ASCR) program. The reports were produced by workshops that brought together researchers from universities, national labs, government, and industry to set priorities for scientific computing.

Professor Felix Herrmann served on the organizing committee for the Workshop on Inverse Methods for Complex Systems under Uncertainty. Assistant Professor Peng Chen joined Herrmann as a workshop participant, contributing expertise in data science and machine learning.

Inverse methods work backward from outcomes to find their causes. Scientists use these tools to study complex systems, like designing new materials with targeted properties and using past wildfires to map vulnerable areas and behavior of future fires.

The ASCR report highlighted Herrmann’s work on seismic exploration and monitoring through digital twins. Founded on inverse methods, digital twins upgrade from static models to virtual systems that accurately mirror their physical counterparts. 

Digital twins integrate real-time data sources, including fluid flows, monitoring and control systems, risk assessments, and human decisions. These models also account for uncertainty and address data gaps or limitations. 

The DOE organized the workshop to support the growing role of inverse modeling. The group identified four priority research directions (PRDs) to guide future work. The PRDs are:

• PRD 1: Discovering, exploiting, and preserving structure
• PRD 2: Identifying and overcoming model limitations
• PRD 3: Integrating disparate multimodal and/or dynamic data
• PRD 4: Solving goal-oriented inverse problems for downstream tasks

“A digital twin is a system you can control, like to optimize operations or to minimize risk,” said Herrmann, who holds joint appointments in the Schools of Earth and Atmospheric Sciences, Electrical and Computer Engineering, and Computational Science and Engineering.

“Digital twins give you a principled way to consider uncertainties, which there are a lot in subsurface monitoring. If you inject carbon dioxide too fast, you will will increase the pressure and may fracture the rock. If you inject too slow, then the process may become too costly. Digital twins help us make balanced decisions under uncertainty.”

Supercomputers, algorithms, and artificial intelligence now power modern science. However, these tools consume enormous amounts of energy. This raises concerns about how to sustain computing and scientific research as we know them in the decades ahead.

Professors Rich Vuduc and Hyesoon Kim co-authored the report from the Workshop on Energy-Efficient Computing for Science. At the three-day ASCR workshop, participants identified five key research directions:

• PRD 1: Co-design energy-efficient hardware devices and architectures for important workloads
• PRD 2: Define the algorithmic foundations of energy-efficient scientific computing
• PRD 3: Reconceptualize software ecosystems for energy efficiency
• PRD 4: Enable energy-efficient data management for data centers, instruments, and users
• PRD 5: Develop integrated, scalable energy measurement and modeling capabilities for next-generation computing systems

“I’m cautiously optimistic about the future of energy-efficient computing. The ASCR report says, from a technological point of view, there are things we can do,” said Vuduc.

“The report lays out paths for how we might design better apps, hardware systems, and algorithms that will use less energy. This is recognition that we should think about how architectures and software work together to drive down energy usage for systems.”

As artificial intelligence (AI) drives explosive growth in data centers, communities across the U.S. are facing rising electricity costs, new industrial development, and mounting strain on an aging power grid.

At Georgia Tech, several faculty members are approaching these sustainability challenges from different but complementary angles: examining how data center policy affects local communities, modeling how AI-driven demand reshapes regional energy systems, and building tools that help the public understand the tradeoffs embedded in grid planning. Together, their work highlights how better data, thoughtful policy, and public engagement can guide more resilient and equitable decisions in an AI-powered future.

AI’s Hidden Footprint: How Data Centers Reshape Communities

Ahmed Saeed studies the infrastructure most people never see. An assistant professor in the School of Computer Science and a Brook Byers Institute for Sustainable Systems (BBISS) Faculty Fellow, Saeed focuses on how data centers — the backbone of modern AI — are built, operated, and regulated, and what their growth means for host communities.

“Data centers are the infrastructure for our digital life, so more of them are necessary to keep doing what we’re doing,” he said.

Data center energy consumption could double or triple by 2028, accounting for up to 12% of U.S. electricity use, according to a report by Lawrence Berkeley National Laboratory. U.S. spending on data center construction jumped nearly 70% between May 2023 and May 2024, according to the American Edge Project.

Georgia is an AI data center hub, ranked fourth globally, with $4.6 billion in AI-related venture capital invested across 368 deals, the American Edge Project reported. At a recent town hall in DeKalb County, Georgia, Saeed helped residents connect AI’s promise to its local consequences. Training large AI models can require tens of thousands of graphics processing units (GPUs) running for days or weeks, driving an unprecedented wave of data center construction. AI-focused chips, he noted, can consume 10 to 14 times more power than traditional processors.

That demand often shows up as pressure on local infrastructure. Communities are increasingly concerned about electricity and water use, grid upgrades, and who ultimately pays. In Virginia, Saeed pointed to a legal dispute in which consumer advocates warned that data centers could raise electricity bills by 5% in the short term and up to 50% over time, while utilities argued those investments were inevitable and could benefit customers in the long run.

Environmental concerns add another layer. Saeed cited controversies over water use and backup diesel generators in states, including Georgia and Tennessee, alongside a recent Environmental Protection Agency (EPA) ruling that tightened generator regulations. While diesel generators are clearly harmful, he cautioned that long-term, rigorous evidence linking data centers to regional health impacts remains limited.

Saeed’s research aims to reduce those impacts directly. By optimizing how workloads are scheduled across large server fleets, his team has demonstrated power savings of 4 – 12%, a meaningful gain if U.S. data centers approach projected levels of up to 12% of national electricity use by 2028.

For Saeed, data centers are akin to highways: essential to modern life, disruptive to nearby communities, and shaped by policy choices. The question, he argues, is not whether AI infrastructure should exist, but how transparently and fairly it is built.

Economist Probes the Energy Costs of the AI Boom

While headlines often frame AI as an energy crisis, Georgia Tech environmental and energy economist and BBISS Faculty Fellow Tony Harding is focused on measuring its real — and uneven — impacts. Harding, an assistant professor in the Jimmy and Rosalynn Carter School of Public Policy, uses economic modeling to examine how AI adoption affects energy use, emissions, and local communities.

In recent work published in Environmental Research Letters, Harding and his co-author analyzed how productivity gains from AI could influence national energy demand. Their findings suggest that, at a macro level, AI-related activity may increase annual U.S. energy use by about 0.03% and CO₂ emissions by roughly 0.02%.

“Those numbers are small in the context of the overall economy,” Harding said. “But the impacts are highly uneven.”

That unevenness is evident in where data centers are built. While Northern Virginia remains the country’s top data center hub, with 343 operational data centers, states like Georgia, which currently has 94 operational data centers, are rapidly attracting facilities due to reliable power and favorable tax policies. 

Harding’s latest research focuses on local effects, asking why data centers cluster in urban areas, how they influence housing markets, what happens to electricity prices, and whether they exacerbate water stress. Early evidence suggests large facilities can increase local electricity rates, contributing to public backlash and regulatory response. In Georgia, the Public Service Commission has begun requiring new, high power draw customers (like data centers) to cover more of the costs associated with grid expansion.

Harding’s goal is to give policymakers better evidence to design incentives and guardrails. “To manage these technologies responsibly,” he said, “we need a clear picture of their intended and unintended consequences.”

Gamifying a Strained and Aging Power Grid

Daniel Molzahn is tackling another side of the problem: how to modernize an aging power grid under growing demand. Electricity demand is expected to rise about 25% by 2030, driven by data centers, electric vehicles, and broadscale electrification. At the same time, much of the U.S. electricity grid is nearing the end of its lifespan, with many transformers being decades old.

To make these challenges tangible, Molzahn, an associate professor in the School of Electrical and Computer Engineering, developed a browser-based game with a group of students through Georgia Tech’s Vertically Integrated Projects program called Current Crisis. Players take on the role of a utility decision-maker, balancing reliability, wildfire risk, renewable integration, and affordability.

The game grew out of Molzahn’s National Science Foundation CAREER award and reflects his belief that complex systems are best understood experientially. Its initial focus is wildfire resilience, modeling how grid infrastructure can both spark and suffer damage from fires.

But resilience comes at a cost. Burying power lines, for example, reduces wildfire risk but dramatically increases expenses. Players must confront the same tradeoffs utilities face: improve reliability or keep rates low.

Molzahn hopes the game will help students and the public grapple with the realities of planning future power systems. “These choices aren’t abstract,” he said. “They shape affordability, resilience, and our path toward a cleaner grid.”

The project now involves nearly 40 students from across campus, supported by Sustainability NEXT funding and a collaboration with Jessica Roberts, former BBISS Faculty Fellow and director of the Technology-Integrated Learning Environments (TILES) Lab in the School of Interactive Computing.

“As a learning scientist, I look at how to engage people with science and scientific data and get people having conversations they might not otherwise have,” says Roberts, who hopes the seed grant helps the team determine first that they are going in the right direction and, second, how to broaden the impact.

One student, Stella Quinto Lima, a graduate research assistant in Human-Centered Computing, has made the game the focus of her doctoral thesis. Through the game, she wants players to notice their misconceptions about the power grid, energy use, and AI, and to use critical thinking to identify, question, and possibly undo those misconceptions.

 “I hope that we can really engage adults and help them see it’s not black and white. The game is not only about power grids, but how AI affects the grid, how it affects our lives, and how it will impact our future.”

The team plans to expand the game’s features, use it in outreach programs, and analyze player decisions as a source of data to study energy-system decision-making.

“We want to change the conversation about power and power grid stability, reliability, and sustainability, Roberts said, “and find a way to get this message to a larger public.”

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.

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.

To address that challenge, researchers at the Georgia Tech Research Institute (GTRI) have developed an improved cryogenic vacuum chamber that helps reduce some common noise sources by isolating ions from vibrations and shielding them from magnetic field fluctuations. The new chamber also incorporates an improved imaging system and a radio frequency (RF) coil that can be used to drive ion transitions from within the chamber. 
 

“There’s a lot of excitement around quantum computing today, and trapped ions are just one of the research platforms available, each with their own benefits and drawbacks,” explained Darian Hartsell, a GTRI research scientist who leads the project. “We are trying to mitigate multiple sources of noise in this chamber and make other improvements with one robust new design.”
 

The chamber design is described in a paper published January 20, 2026 in the journal Applied Physics Letters. Some of the technical improvements developed for the project are already being applied at GTRI and collaborating organizations. This work was done in collaboration with Los Alamos National Laboratory.
 

The goal of the vibration isolation is to reduce the laser amplitude and phase noise when addressing the ions, increasing operation fidelity. The goal of the magnetic field noise reduction is to preserve the coherence of qubits for longer periods of time so researchers can use them for more complex algorithms.

See the complete article on the GTRI news site

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.

 “What is happening within the field is revolutionary,” says School of Earth and Atmospheric Sciences Associate Chair and Professor Annalisa Bracco, adding that because many climate-related processes — from ocean currents to melting glaciers and weather patterns — can be described with physical equations, these advancements have the potential to help us understand and predict climate in critically important ways. 

Bracco is the lead author of a new review paper providing a comprehensive look at the intersection of AI and climate physics.

The result of an international collaboration between Georgia Tech’s Bracco, Julien Brajard (Nansen Environmental and Remote Sensing Center), Henk A. Dijkstra (Utrecht University), Pedram Hassanzadeh (University of Chicago), Christian Lessig (European Centre for Medium-Range Weather Forecasts), and Claire Monteleoni (University of Colorado Boulder), the paper, ‘Machine learning for the physics of climate,’ was recently published in Nature Reviews Physics. 

“One of our team’s goals was to help people think deeply on how climate science and AI intersect,” Bracco shares. “Machine learning is allowing us to study the physics of climate in a way that was previously impossible. Coupled with increasing amounts of data and observations, we can now investigate climate at scales and resolutions we’ve never been able to before.”

Connecting hidden dots

The team showed that ML is driving change in three key areas: accounting for missing observational data, creating more robust climate models, and enhancing predictions, especially in weather forecasting. However, the research also underscores the limits of AI — and how researchers can work to fill those gaps.

“Machine learning has been fantastic in allowing us to expand the time and the spatial scales for which we have measurements,” says Bracco, explaining that ML could help fill in missing data points — creating a more robust record for researchers to reference. However, like patching a hole in a shirt, this works best when the rest of the material is intact.

“Machine learning can extrapolate from past conditions when observations are abundant, but it can’t yet predict future trends or collect the data we need,” Bracco adds. “To keep advancing, we need scientists who can determine what data we need, collect that data, and solve problems.”

Modeling climate, predicting weather

Machine learning is often used when improving climate models that can simulate changing systems like our atmosphere, oceans, land, biochemistry, and ice. “These models are limited because of our computing power, and are run on a three-dimensional grid,” Bracco explains: below the grid resolution, researchers need to approximate complex physics with simpler equations that computers can solve quickly, a process called ‘parameterization’.

Machine learning is changing that, offering new ways to improve parameterizations, she says. “We can run a model at extremely high resolutions for a short time, so that we don’t need to parameterize as many physical processes — using machine learning to derive the equations that best approximate what is happening at small scales,” she explains. “Then we can use those equations in a coarser model that we can run for hundreds of years.”

While a full climate model based solely on machine learning may remain out of reach, the team found that ML is advancing our ability to accurately predict weather systems and some climate phenomena like El Niño. 

Previously, weather prediction was based on knowing the starting conditions — like temperature, humidity, and barometric pressure — and running a model based on physics equations to predict what might happen next. Now, machine learning is giving researchers the opportunity to learn from the past. “We can use information on what has happened when there were similar starting conditions in previous situations to predict the future without solving the underlying governing equations,” Bracco says. “And all while using orders-of-magnitude less computing resources.”

The human connection

Bracco emphasizes that while AI and ML play a critical role in accelerating research, humans are at the core of progress. “I think the in-person collaboration that led to this paper is, in itself, a testament to the importance of human interaction,” she says, recalling that the research was the result of a workshop organized at the Kavli Institute for Theoretical Physics — one of the team’s first in-person discussions after the Covid-19 pandemic.

“Machine learning is a fantastic tool — but it's not the solution to everything,” she adds. “There is also a real need for human researchers collecting high-quality data, and for interdisciplinary collaboration across fields. I see this as a big challenge, but a great opportunity for computer scientists and physicists, mathematicians, biologists, and chemists to work together.”

Funding: National Science Foundation, European Research Council, Office of Naval Research, US Department of Energy, European Space Agency, Choose France Chair in AI.

DOI: https://doi.org/10.1038/s42254-024-00776-3

Students and faculty from the School of Computational Science and Engineering (CSE) are leading the Georgia Tech contingent at the SIAM Conference on Computational Science and Engineering (CSE25). The Society of Industrial and Applied Mathematics (SIAM) organizes CSE25, occurring March 3-7 in Fort Worth, Texas.

At CSE25, the School of CSE researchers are presenting papers that apply computing approaches to varying fields, including:                   

• Experiment designs to accelerate the discovery of material properties
• Machine learning approaches to model and predict weather forecasting and coastal flooding
• Virtual models that replicate subsurface geological formations used to store captured carbon dioxide
• Optimizing systems for imaging and optical chemistry
• Plasma physics during nuclear fusion reactions

[Related: GT CSE at SIAM CSE25 Interactive Graphic] 

“In CSE, researchers from different disciplines work together to develop new computational methods that we could not have developed alone,” said School of CSE Professor Edmond Chow. 

“These methods enable new science and engineering to be performed using computation.” 

CSE is a discipline dedicated to advancing computational techniques to study and analyze scientific and engineering systems. CSE complements theory and experimentation as modes of scientific discovery. 

Held every other year, CSE25 is the primary conference for the SIAM Activity Group on Computational Science and Engineering (SIAG CSE). School of CSE faculty serve in key roles in leading the group and preparing for the conference.

In December, SIAG CSE members elected Chow to a two-year term as the group’s vice chair. This election comes after Chow completed a term as the SIAG CSE program director. 

School of CSE Associate Professor Elizabeth Cherry has co-chaired the CSE25 organizing committee since the last conference in 2023. Later that year, SIAM members reelected Cherry to a second, three-year term as a council member at large. 

At Georgia Tech, Chow serves as the associate chair of the School of CSE. Cherry, who recently became the associate dean for graduate education of the College of Computing, continues as the director of CSE programs. 

“With our strong emphasis on developing and applying computational tools and techniques to solve real-world problems, researchers in the School of CSE are well positioned to serve as leaders in computational science and engineering both within Georgia Tech and in the broader professional community,” Cherry said. 

Georgia Tech’s School of CSE was first organized as a division in 2005, becoming one of the world’s first academic departments devoted to the discipline. The division reorganized as a school in 2010 after establishing the flagship CSE Ph.D. and M.S. programs, hiring nine faculty members, and attaining substantial research funding.

Ten School of CSE faculty members are presenting research at CSE25, representing one-third of the School’s faculty body. Of the 23 accepted papers written by Georgia Tech researchers, 15 originate from School of CSE authors.

The list of School of CSE researchers, paper titles, and abstracts includes:
Bayesian Optimal Design Accelerates Discovery of Material Properties from Bubble Dynamics
Postdoctoral Fellow Tianyi Chu, Joseph Beckett, Bachir Abeid, and Jonathan Estrada (University of Michigan), Assistant Professor Spencer Bryngelson
[Abstract]

Latent-EnSF: A Latent Ensemble Score Filter for High-Dimensional Data Assimilation with Sparse Observation Data
Ph.D. student Phillip Si, Assistant Professor Peng Chen
[Abstract]

A Goal-Oriented Quadratic Latent Dynamic Network Surrogate Model for Parameterized Systems
Yuhang Li, Stefan Henneking, Omar Ghattas (University of Texas at Austin), Assistant Professor Peng Chen
[Abstract]

Posterior Covariance Structures in Gaussian Processes
Yuanzhe Xi (Emory University), Difeng Cai (Southern Methodist University), Professor Edmond Chow
[Abstract]

Robust Digital Twin for Geological Carbon Storage
Professor Felix Herrmann, Ph.D. student Abhinav Gahlot, alumnus Rafael Orozco (Ph.D. CSE-CSE 2024), alumnus Ziyi (Francis) Yin (Ph.D. CSE-CSE 2024), and Ph.D. candidate Grant Bruer
[Abstract]

Industry-Scale Uncertainty-Aware Full Waveform Inference with Generative Models
Rafael Orozco, Ph.D. student Tuna Erdinc, alumnus Mathias Louboutin (Ph.D. CS-CSE 2020), and Professor Felix Herrmann
[Abstract]

Optimizing Coupled Systems: Insights from Co-Design Imaging and Optical Chemistry
Assistant Professor Raphaël Pestourie, Wenchao Ma and Steven Johnson (MIT), Lu Lu (Yale University), Zin Lin (Virginia Tech)
[Abstract]

Multifidelity Linear Regression for Scientific Machine Learning from Scarce Data
Assistant Professor Elizabeth Qian, Ph.D. student Dayoung Kang, Vignesh Sella, Anirban Chaudhuri and Anirban Chaudhuri (University of Texas at Austin)
[Abstract]

LyapInf: Data-Driven Estimation of Stability Guarantees for Nonlinear Dynamical Systems
Ph.D. candidate Tomoki Koike and Assistant Professor Elizabeth Qian
[Abstract]

The Information Geometric Regularization of the Euler Equation
Alumnus Ruijia Cao (B.S. CS 2024), Assistant Professor Florian Schäfer
[Abstract]

Maximum Likelihood Discretization of the Transport Equation
Ph.D. student Brook Eyob, Assistant Professor Florian Schäfer
[Abstract]

Intelligent Attractors for Singularly Perturbed Dynamical Systems
Daniel A. Serino (Los Alamos National Laboratory), Allen Alvarez Loya (University of Colorado Boulder), Joshua W. Burby, Ioannis G. Kevrekidis (Johns Hopkins University), Assistant Professor Qi Tang (Session Co-Organizer)
[Abstract]

Accurate Discretizations and Efficient AMG Solvers for Extremely Anisotropic Diffusion Via Hyperbolic Operators
Golo Wimmer, Ben Southworth, Xianzhu Tang (LANL), Assistant Professor Qi Tang 
[Abstract]

Randomized Linear Algebra for Problems in Graph Analytics
Professor Rich Vuduc
[Abstract]

Improving Spgemm Performance Through Reordering and Cluster-Wise Computation
Assistant Professor Helen Xu
[Abstract]

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)

Imagine stepping into a space the size of multiple football fields — only instead of turf and goalposts, it’s filled with science. Every inch is alive with posters, equipment demos, and researchers sharing the latest breakthroughs.  

Inspired by SpaceX’s Super Heavy booster, a team led by Georgia Tech’s Spencer Bryngelson and New York University’s Florian Schäfer modeled the turbulent interactions of a 33-engine rocket. Their experiment set new records, running the largest ever fluid dynamics simulation by a factor of 20 and the fastest by over a factor of four.

The team ran its custom software on the world’s two fastest supercomputers, as well as the eighth fastest, to construct such a massive model.

Applications from the simulation reach beyond rocket science. The same computing methods can model fluid mechanics in aerospace, medicine, energy, and other fields. At the same time, the work advances understanding of the current limits and future potential of computing. 

The team finished as runners-up for the 2025 Gordon Bell Prize for its impactful, multi-domain research. Referred to as the Nobel Prize of supercomputing, the award was presented at the world’s top conference for high-performance computing (HPC) research.

“Fluid dynamics problems of this style, with shocks, turbulence, different interacting fluids, and so on, are a scientific mainstay that marshals our largest supercomputers,” said Bryngelson, an assistant professor with the School of Computational Science and Engineering (CSE).

“Larger and faster simulations that enable solutions to long-standing scientific problems, like the rocket propulsion problem, are always needed. With our work, perhaps we took a big dent out of that issue.”

The Super Heavy booster reflects the space industry’s move toward reusable multi-engine first-stage rockets that are easier to transport and more economical overall. 

However, this shift creates research and testing challenges for new designs.

Each of Super Heavy’s 33 thrusters expels propellant at ten times the speed of sound. As individual engines reach extreme temperatures, pressures, and densities, their combined interactions with the airframe make such violent physics even more unpredictable.

Frequent physical experiments would be expensive and risky, so scientists rely on computer models to supplement the engineering process. 

Bryngelson’s flagship Multicomponent Flow Code (MFC) software anchored the experiment. MFC is an open-source computer program that simulates fluid dynamic models. Bryngelson’s lab has been modifying MFC since 2022 to run on more powerful computers and solve larger problems. 

In computing terms, this MFC-enhanced model simulated fluid flow resolution at 200 trillion grid points and one quadrillion degrees of freedom. These metrics exceeded previous record-setting benchmarks that tallied 10 trillion and 30 trillion grid points.

This means MFC simulations provide greater detail and capture smaller-scale features than previous approaches. The rocket simulation also ran four times faster and achieved 5.7 times the energy efficiency of comparable methods.   

Integrating information geometric regularization (IGR) into MFC played a key role in attaining these results. This new approach improved the simulation’s computational efficiency and overcame the challenge of shock dynamics.

In fluid mechanics, shock waves occur when objects move faster than the speed of sound. Along with hampering the performance of airframes and propulsion systems, shocks have historically been difficult to simulate.

Computational scientists have used empirical models based on artificial viscosity to account for shocks. Although these approaches mimic the physical effects of shock waves at the microscopic scale, they struggle to effectively capture the large-scale features of the flow. 

Information geometry uses curved spaces to study concepts of statistics and information. IGR uses these tools to modify the underlying geometry in fluid dynamics equations. When traveling in the modified geometry, fluid in the model preserves the shocks in a more natural way. 

“When regularizing shocks to much larger scales relevant in these numerical simulations, conventional methods smear out important fine-scale details,” said Schäfer, an assistant professor at NYU’s Courant Institute of Mathematical Sciences.

“IGR introduces ideas from abstract math to CFD that allow creating modified paths that approach the singularity without ever reaching it. In the resulting fluid flow, shocks never become too spiky in simulations, but the fine-scale details do not smear out either.” 

Simulating a model this large required the Georgia Tech researchers to run MFC on El Capitan and Frontier, the world's two fastest supercomputers. 

The systems are two of four exascale machines in existence. This means they can solve at least one quintillion (“1” followed by 18 zeros) calculations per second. If a person completed a simple math calculation every second, it would take that person about 30 billion years to reach one quintillion operations.

Frontier is housed at Oak Ridge National Laboratory and debuted as the world’s first exascale supercomputer in 2022. El Capitan surpassed Frontier when Lawrence Livermore National Laboratory launched it in 2024.

To prepare MFC for performance on these machines, Bryngelson’s lab followed a methodical approach spanning years of hardware acquisition and software engineering. 

In 2022, Bryngelson attained an AMD MI210 GPU accelerator. Optimizing MFC on the component played a critical step toward preparing the software for exascale machines.

AMD hardware underpins both El Capitan and Frontier. The MI300A GPU powers El Capitan while Frontier uses the MI250X GPU. 

After configuring MFC on the MI210 GPU, Bryngelson’s lab ran the software on Frontier for the first time during a 2023 hackathon. This confirmed the code was ready for full-scale deployment on exascale supercomputers based on AMD hardware. 

In addition to El Capitan and Frontier, the simulation ran on Alps, the world’s eight-fastest supercomputer based at the Swiss National Supercomputing Centre. It is the largest available system that features the NVIDIA GH200 Grace Hopper Superchip.

Like with AMD GPUs, Bryngelson acquired four GH200s in 2024 and began configuring MFC to the latest hardware innovation powering New Age supercomputers. Later that year, the Jülich Research Centre accepted Bryngelson’s group into an early access program to test JUPITER, a developing supercomputer based on the NVIDIA superchip.

The group earned a certificate for scaling efficiency and node performance on the way toward validating that their code worked on the GH200. The early access project proved successful for JUPITER, which launched in 2025 as Europe’s fastest supercomputer and fourth fastest in the world.

“Getting the level of hands-on experience with world-leading supercomputers and computing resources at Georgia Tech through this project has been a fantastic opportunity for a grad student,” said CSE Ph.D. student Ben Wilfong.

“To leverage these machines, I learned more advanced programming techniques that I’m glad to have in my tool belt for future projects. I also enjoyed the opportunity to work closely with and learn from industry experts from NVIDIA, AMD, and HPE/Cray.”

El Capitan, Frontier, JUPITER, and Alps maintained their rankings at the 2025 International Conference for High Performance Computing Networking, Storage and Analysis (SC25). Of note, the TOP500 announced at SC25 that JUPITER surpassed the exaflop threshold. 

The SC Conference Series is one of two venues where the TOP500 announces updated supercomputer rankings every June and November. The TOP500 ranks and details the 500 most powerful supercomputers in the world. 

The SC Conference Series serves as the venue where the Association for Computing Machinery (ACM) presents the Gordon Bell Prize. The annual award recognizes achievement in HPC research and application. The Tech-led team was among eight finalists for this year’s award.

Along with Bryngelson, Georgia Tech members included Ph.D. students Anand Radhakrishnan and Wilfong, postdoctoral researcher Daniel Vickers, alumnus Henry Le Berre (CS 2025), and undergraduate student Tanush Prathi.

Schäfer’s partnership with the group stems from his previous role as an assistant professor at Georgia Tech from 2021 to 2025. 

Collaborators on the project included Nikolaos Tselepidis and Benedikt Dorschner from NVIDIA, Reuben Budiardja from ORNL, Brian Cornille from AMD, and Stephen Abbot from HPE. All were co-authors of the paper and named finalists for the Gordon Bell Prize. 

“I’m elated that we have been nominated for such a prestigious award. It wouldn't have been possible without the combined and diligent efforts of our team,” Radhakrishnan said. 

“I’m looking forward to presenting our work at SC25 and connecting with other researchers and fellow finalists while showcasing seminal work in the field of computing.”

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  

Workshops hosted by the Robert C. Williams Museum of Papermaking and led by Georgia Tech Assistant Professor HyunJoo Oh will introduce about 60 students from Atlanta Public Schools to paper-based electronics through hands-on workshops.

The Williams Museum will open an exhibit titled “The Future of Paper” that displays designs created in the workshop alongside visionary examples of paper-based technologies from Georgia Tech researchers.

The exhibit, funded by the National Science Foundation, is slated to open to the public in 2027.

Oh is a researcher with joint appointments in the School of Interactive Computing and the School of Industrial Design.She leads the Computational Design and Craft (CoDe Craft) Group at Georgia Tech, where her team integrates everyday craft materials with computing to support creative exploration.

Oh believes paper could be widely used to support prototyping printed circuit boards (PCBs) as a sustainable alternative to silicon. While silicon is the most prominent material used by technology companies to build computer chips, it isn’t biodegradable. And it can be harmful to the environment and contribute to e-waste. 

Paper, however, provides an eco-friendly platform for printing conductive traces and mounting small electronic components. With the expansion of printed electronic tools and techniques, paper and similar materials have become more popular among technologists who develop sensing technologies and wearable devices.

“It’s widely available and accessible,” Oh said. “I can’t think of anything more affordable and approachable that young makers and the broader maker community can use for circuits than paper.

“Printed electronics traditionally required expensive equipment, but with recent innovation in materials science, conductive materials such as conductive pens and paint available in local arts and crafts stores can be used to build circuits on paper. We can also print circuits using a regular office inkjet printer with silver ink.”

Shared Vision

Shortly after arriving at Georgia Tech in 2019, Oh knew she had to develop a project that would let her partner with the Williams Museum. 

“I was captivated by the museum’s space and its celebration of paper,” she said. “I wanted a collaboration that would integrate technology in a way that complemented and respected the museum’s existing beauty.”

Museum director Virginia Howell said the project was a perfect match for the museum, which has documented the history of papermaking since it was founded in 1939 by the Massachusetts Institute of Technology. Georgia Tech became the new home of the museum in 2003.

With more than 100,000 objects in its collection — some dating back as far as 2,000 years ago — the museum is unique, Howell said. Most papermaking museums are typically located at an historic mill, but the Williams Museum covers the history of papermaking.

Howell said that before she met Oh, she had been looking for an exhibit that would display the possible future of papermaking.

“We do the past of paper fantastically well, and we do the present of paper well through our changing exhibitions,” Howell said. “The future of paper is something we haven’t spent a lot of time interpreting.”

Crafting the Future

Oh and Howell agree that young people will shape that future. Oh said paper is commonly linked to art in the education sphere. As the material’s use in technology increases, however, it can funnel the interests of students toward engineering and computing. 

Incorporating paper and craft materials can invite more students to explore engineering and computing concepts. After all, a circuit board created on paper isn’t so different from one built on a silicon PCB, Oh said.

“This approach can excite the kind of students who usually feel disconnected from electronics and computing,” she said. “It gives those who only see themselves as creative or artistic a way to enjoy technology and resonate with it.

“Usually when I work with young students, especially girls, if I start with something technical, their interest wanes. But when I present those same ideas through art using familiar materials like paper, they become more engaged and confident. That’s when they start to flourish.”

Oh and Howell will hold three rounds of 10-week workshops for the students — spring 2026, fall 2026, and spring 2027. The best designs from those workshops will be displayed in the exhibit.

“They’ll feel more comfortable with computing and engineering as an introductory experience,” Howell said. “When they successfully build on it and realize they did this on a sheet of paper, it’s exciting to think what they’ll do when they get more sophisticated tools and access.”

As one of Georgia Tech’s 11 interdisciplinary research institutes, IMS is designed to break down silos between traditional academic units. By operating core user facilities and fostering collaborative research, IMS creates a unique ecosystem where device-level innovation meets systems-level design. This event personified that mission by connecting researchers who typically work on different ends of the stack.

“We’re looking for opportunities to bring people together to have discussions that are both informative and potentially create a little bit of friction in the best possible way around trending topics in science and engineering,” said Mike Filler, IMS deputy director, during opening remarks.

The panel was moderated by Divya Mahajan, assistant professor in the School of Electrical and Computer Engineering, and featured Moinuddin Qureshi, professor of computer science; Anand Iyer, assistant professor of computer science; and Asif Khan, associate professor in electrical and computer engineering. 

The discussion explored the dynamics between compute abundance and energy constraints. As AI models scale up, power consumption has become a societal issue, driving up energy demands and even influencing political conversations. The panelists agreed that the bottleneck isn’t compute — a computer’s ability to process and execute tasks — but data movement. Moving data uses 100 to 1,000 times more energy than computation, making memory systems the critical frontier.

The conversation highlighted how breakthroughs in compute must occur at every layer — from individual devices to full computer systems. At the device level, Khan mentioned emerging memory technologies and “beyond CMOS” approaches such as embedding compute within memory and exploring bio-inspired architectures.

From a computer architecture level, Qureshi advocated rethinking interfaces and creating designs optimized for the future of computing. AI needs regular patterns to work optimally, and current patterns are not set up for that.

“If you want efficiency, design systems that make sense for AI,” Qureshi said. “Develop new interfaces, develop new modules, architectures, and organization that make for a specific pattern.”

At the systems level, Iyer stressed practical strategies like near-memory compute and energy-aware scheduling while acknowledging the need for co-design between hardware and software.

“Now in terms of brains or bio-inspired computing, my conjecture is that there is currently no hardware that is capable of doing it,” Khan said. He also noted that right now, there is no computer or algorithm that has the scale of computing comparable to human brain power.

The panelists didn’t shy away from provocative ideas — such as whether graphic processing units are the final solution for AI and whether matrix multiplication alone can lead to artificial general intelligence. While opinions varied, all agreed that organizations like IMS are key to bringing together diverse expertise to tackle these questions collaboratively.

The Boundaries and Breakthroughs series continues in January with a panel on bioelectronics and medical technologies, reinforcing IMS’s commitment to fostering dialogue that spans the full spectrum of innovation.

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.”

The event marks the culmination of the semester-long I2P course, where undergraduate students develop functional prototypes aimed at solving real-world problems. Prototypes this semester include a smart military drone, a gentler device for cervical cancer screening, a rotating espresso station, tools to keep AI safe, compact data centers, systems that simulate cyberattacks to help companies strengthen their defenses, and many more. 

The showcase is free and open to students, faculty, staff, and members of the local community. 

Winning teams will receive prizes and a “golden ticket” into CREATE-X’s Startup Launch, a summer accelerator that provides optional seed funding, accounting and legal service credits, mentorship, and more to help students turn their prototypes into viable startups.

This is a free event, and refreshments will be provided. Register for the Fall 2025 I2P Showcase today!

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.”

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.”

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.

Workshops hosted by the Robert C. Williams Museum of Papermaking and led by Georgia Tech Assistant Professor HyunJoo Oh will introduce about 60 students from Atlanta Public Schools to paper-based electronics through hands-on workshops.

The Williams Museum will open an exhibit titled “The Future of Paper” that displays designs created in the workshop alongside visionary examples of paper-based technologies from Georgia Tech researchers.

The exhibit, funded by the National Science Foundation, is slated to open to the public in 2027.

Oh is a researcher with joint appointments in the School of Interactive Computing and the School of Industrial Design.She leads the Computational Design and Craft (CoDe Craft) Group at Georgia Tech, where her team integrates everyday craft materials with computing to support creative exploration.

Oh believes paper could be widely used to support prototyping printed circuit boards (PCBs) as a sustainable alternative to silicon. While silicon is the most prominent material used by technology companies to build computer chips, it isn’t biodegradable. And it can be harmful to the environment and contribute to e-waste. 

Paper, however, provides an eco-friendly platform for printing conductive traces and mounting small electronic components. With the expansion of printed electronic tools and techniques, paper and similar materials have become more popular among technologists who develop sensing technologies and wearable devices.

“It’s widely available and accessible,” Oh said. “I can’t think of anything more affordable and approachable that young makers and the broader maker community can use for circuits than paper.

“Printed electronics traditionally required expensive equipment, but with recent innovation in materials science, conductive materials such as conductive pens and paint available in local arts and crafts stores can be used to build circuits on paper. We can also print circuits using a regular office inkjet printer with silver ink.”

Shared Vision

Shortly after arriving at Georgia Tech in 2019, Oh knew she had to develop a project that would let her partner with the Williams Museum. 

“I was captivated by the museum’s space and its celebration of paper,” she said. “I wanted a collaboration that would integrate technology in a way that complemented and respected the museum’s existing beauty.”

Museum director Virginia Howell said the project was a perfect match for the museum, which has documented the history of papermaking since it was founded in 1939 by the Massachusetts Institute of Technology. Georgia Tech became the new home of the museum in 2003.

With more than 100,000 objects in its collection — some dating back as far as 2,000 years ago — the museum is unique, Howell said. Most papermaking museums are typically located at an historic mill, but the Williams Museum covers the history of papermaking.

Howell said that before she met Oh, she had been looking for an exhibit that would display the possible future of papermaking.

“We do the past of paper fantastically well, and we do the present of paper well through our changing exhibitions,” Howell said. “The future of paper is something we haven’t spent a lot of time interpreting.”

Crafting the Future

Oh and Howell agree that young people will shape that future. Oh said paper is commonly linked to art in the education sphere. As the material’s use in technology increases, however, it can funnel the interests of students toward engineering and computing. 

Incorporating paper and craft materials can invite more students to explore engineering and computing concepts. After all, a circuit board created on paper isn’t so different from one built on a silicon PCB, Oh said.

“This approach can excite the kind of students who usually feel disconnected from electronics and computing,” she said. “It gives those who only see themselves as creative or artistic a way to enjoy technology and resonate with it.

“Usually when I work with young students, especially girls, if I start with something technical, their interest wanes. But when I present those same ideas through art using familiar materials like paper, they become more engaged and confident. That’s when they start to flourish.”

Oh and Howell will hold three rounds of 10-week workshops for the students — spring 2026, fall 2026, and spring 2027. The best designs from those workshops will be displayed in the exhibit.

“They’ll feel more comfortable with computing and engineering as an introductory experience,” Howell said. “When they successfully build on it and realize they did this on a sheet of paper, it’s exciting to think what they’ll do when they get more sophisticated tools and access.”

One of these researchers is Amanda Meng, senior research scientist in the School of Computer Science (SCS). The overarching theme in Meng’s work is the relationship between power and data and how different social groups can make use of data to shift power. 

As the only social scientist in SCS, Meng sees her role as an “important and potentially powerful interdisciplinary connection.” 

Connecting Social Justice with Data 

Although focused on political and social change, Meng’s work has always had links to technology. 

After completing her undergraduate education at Georgia Tech, Meng joined the Peace Corps, where she served in the Dominican Republic. She spent two years there working to improve computer literacy in schools and create community computer labs. 

Meng said her time in the Peace Corps made her interested in how communities advocated for themselves. She explored this idea further while completing her Ph.D. from the Georgia Tech Sam Nunn School of International Affairs. 

With her Ph.D. in hand, Meng was hired as a research scientist in SCS, working under Professor Ellen Zegura and School of Interactive Computing Professor Carl DiSalvo on civic data projects based in Atlanta. 

This experience made her curious about the interaction between data literacy and civic literacy. 

“We live in such a data-fied society that a lot of advocacy work often does involve data because to make your claims legitimate, policy makers want to see and understand the data,” she said. 

Following a brief stint in the private sector as a data consultant, Meng returned to SCS, this time as a research scientist working on IODA (Internet Outage Detection and Analysis) with Associate Professor Alberto Dainotti. IODA is a research project and online platform that provides real-time measurements on global internet connectivity. 

In her contribution to the IODA project, Meng aims to improve the usability of IODA, particularly by users affected by government-ordered shutdowns, by developing IODA users’ internet measurement literacy. Currently, IODA provides the most granular, near-real-time data on Internet infrastructure connectivity. Meng uses this data to collaborate with global advocacy groups to publish reports detailing IODA’s measurements alongside its sociopolitical context. Meng said the eventual goal of her work with IODA is for others to know how to use the platform to monitor for events and advocate against shutdowns. 

“The platform is really only as successful as its userbase is at understanding, making use, and acting on its data,” Meng said. 

In the past year, Meng was awarded her first grant as principal investigator. The grant uses Aggie, an open-source tool developed at Tech that aggregates content from the internet. 

Previously, Aggie has been used to monitor elections on social media. Meng said she wants to explore using it to monitor internet shutdowns or censorship events. She is currently conducting a pilot study to test the system, which will determine whether Aggie offers a more collaborative and coordinated way to monitor connectivity across measurement and social media data. 

The Role of a Research Scientist 

As a research scientist, almost all of Meng’s work is oriented toward research. This includes working on proposals and existing grants, as well as advising students. 

“We love to involve students in our research,” she said. “We aren’t just here to do research. We are here to involve students in research so they can learn and develop domain skills and research skills.” 

Since 2024, Meng has served on the School Advisory Committee in SCS. She says it’s important to have research faculty in service roles, as they have a different set of needs in their position. 

“Through the funding we can apply for, the research we do, and the work we do with students, we are an important multiplier for the work that the School wants to cultivate,” Meng said. 

Community Driven 

Even as a Ph.D. student, Meng said she wanted to contribute to local community groups. An important value she learned in the Peace Corps was to be an active participant in the community she lived in. 

Meng started getting involved in a housing justice project in Atlanta’s Westside neighborhood that was collecting data related to their mission. They soon discovered that some residents’ data was more accurate than official records because they lived there. 

“We also learned it’s not all about impacting legislation,” Meng said. “It’s about mobilizing resources within the community, and the fact that data could be used to do that was an important finding, and it’s something that I want to continue to draw out with data and AI.” 

Meng has continued to work with the group from that project and wants to continue ethnographic research into how data and AI are used to create change. 

“AI could have the ability to consolidate power in the hands of those who develop closed-source models," Meng said. "It’s important to study the entities that are developing AI as much as we study the communities that might make use of or be most minoritized by AI." 

With the help of a $1.25 million grant from the National Science Foundation, the three institutions seek to increase youth input into policymaking and encourage youth-led community organizing.

Youth-designed civic technologies are an effective way to engage youth with their communities, said Andrea Parker, an associate professor in Georgia Tech’s School of Interactive Computing. 

Examples of civic technologies are public data initiatives, citizen science projects, public issue reporting platforms, and digital voting platforms. Parker said the perspectives of young people are often neglected in the design of such technologies.

“We don’t know much about what community issues are important to youth because we haven’t asked them,” she said. “What is their vision for community well-being, and what do they want to address through civic technology?”

Parker is the lead principal investigator (PI) on the project that will engage youth from low socio-economic communities in Atlanta and Boston. She said the youth will decide what technologies will be created, but they could include a mobile app or a publicly accessible platform.

“We’re interested in studying how technologies can help youth become more civically engaged in their communities and build social connection, trust, and belonging amongst neighbors,” she said. 

“Youth in lower-income neighborhoods face increased threats to their mental health. Socially cohesive communities can counteract those barriers and are essential for youth well-being.”

Parker added that impoverished communities often have less social cohesion compare to wealthier areas. Higher-income neighborhoods often have more access to resources that support social cohesion and civic engagement. 

Backed by Data

Brooke Foucault Welles, co-PI, professor, and interim dean at Northeastern’s College of Media, Arts and Design, said she’s interested in seeing which issues the youths from both Atlanta and Boston will address through their design process. Studying and working with youth across these geographic settings will help the team identify how civic technology can best support youth in varied neighborhood contexts.

The project will also advance data literacy among young people as they collect and study data to support the new technologies. Welles said data-centered advocacy increases young people’s chances of being heard by elder community members.

“Empowering young people to use data when they’re making their arguments about what matters to them and to their communities is the point of this project,” she said. “It makes their arguments more compelling if they can present data to the adult members of their communities about what’s going on.”

The project’s reach could expand beyond Atlanta and Boston.

Once the technologies are designed, the researchers will package them and make them publicly available as a toolkit. 

If successful, the project could drive a movement toward more collective organizing to ensure the youth perspective gets factored into community decision-making. 

“They’re a vital part of our communities, and they’re the ones for whom our decisions have the biggest impact,” Welles said. “These are the times when they’re forming their own civic identities, so engaging them in civic life has long ripple effects. We create more active and thoughtful citizens when we engage young people with civic life.”

AIxCC was a two-year long competition to create an artificial intelligence (AI) enabled cyber reasoning system capable of autonomously finding and patching vulnerabilities.

“This is a once in a generation competition organized by DARPA about how to utilize recent advancements in AI to use in security related tasks,” said Georgia Tech Professor Taesoo Kim.

“As hackers we started this competition as AI skeptics, but now we truly believe in the potential of adopting large language models (LLM) when solving security problems."

The Atlantis system was Team Atlanta’s submission. Atlantis is a fuzzer- or an automated software that finds vulnerabilities or bugs- and enhanced it with several different types of LLMs.

While developing the system, Team Atlanta reported the heat put out by the GPU rack was hot enough to roast marshmallows.

The team was comprised of hackers, engineers, and cybersecurity researchers. The Georgia Tech alumni on the team also represented their employers which include KAIST, POSTECH, and Samsung Research. Kim is also the vice president of Samsung Research. 

CBF Isekai is sponsored by SON Technologies — short for Swagged Out Nerds — a Macon esports company focused on workforce development. SON believes the best gamers can also become promising IT professionals. 

A startup founded by two Air Force veterans, SON is already making a name for itself in the esports world and has support from Georgia Tech. It is one of the Accelerate companies in the startup portfolio of Tech’s Advanced Technology Development Center (ATDC), one of the oldest and most successful university-affiliated incubators in the United States.

Swagged Out Start

SON founders Jason Clarke and John Robinson first met when they both worked in cybersecurity in the Air Force. As they transitioned to civilian IT careers, they realized a perhaps unlikely source sparked their IT expertise — video games. In 2019, the two partnered to create an esports competition team for veterans, but they knew the company’s mission could be bigger.

“When people think of gamers, you think of a 40-year-old person in their mom’s basement,” Clarke said. “But we wanted to change the perception. Gamers have employable skills that can be used for substantial IT work.”

For example, when a person plays a multiplayer game like Fortnite, they can assume a leadership role, delivering directives to their teams. What may look like mere play actually entails planning, organizing, and executing. Even a simple task like troubleshooting a household wi-fi network is a skill that can be expanded on with the right training.

From Player to Professional

SON wants both kid and adult gamers to know they have options. They regularly host gaming tournaments and conventions to find people who would be right for their programs and cultivate community. Through a partnership with digital education company Aperion Global Institute and cybersecurity certification organization EC-Council, Clarke and Robinson administer a high school-level curriculum highlighting the synergies between IT and gaming. 

Adults also have opportunities. Past SON tournament competitors can take an eight-week program, Sticks to Clicks, to turn their gaming skills into IT proficiency. These initiatives come at a crucial time: Between now and 2030, according to O*NET OnLine, 51,000 cybersecurity jobs in the state of Georgia are expected to be vacant. 

Game-Changing Career Paths

The programs’ benefits are already tangible. One adult participant in Sticks to Clicks had an annual income of less than $10,000 before joining the program. In the first seven weeks, he earned a certification in CompTIA Security+. In the eighth and final week, he interviewed with some of SON’s workforce partners. He was ultimately hired to install network infrastructure for $46,000 a year. 

High school students have had similar success. In the 2025-26 school year alone, 150 students went through the SON program and received stackable credentials that can prepare them for IT careers even if they don’t go to college. 

All of this momentum got ATDC’s attention, and SON Tech was accepted as a portfolio company in Fall 2024. Both Georgia AIM and the Air Force went to Macon for the 2025 Isekai convention and met potential employees firsthand. They saw that SON was just getting started.

The ATDC Connection

SON joined ATDC in 2024 under the AI and Manufacturing vertical sponsored by Georgia AIM, a statewide coalition to advance manufacturing using AI. SON is one of ATDC’s first middle Georgia companies, but the entire state will experience benefits. Through ATDC, SON can use Georgia Tech resources, meet experts in grant applications and corporate networking, and plug into the startup ecosystem in Atlanta. The three-to-five-year program helps startups scale up. 

“The truth is when you’re starting a company, the first few years are the worst of your life,” said Nwanyinma Dike, who serves as the Georgia AIM and ATDC liaison. In this role, she advises SON. “Connecting into a community of folks rooting for you, listening to you, helping you breathe through whatever challenges occur is one of the most valuable resources ATDC has to offer.”

The size of the March Isekai event was only possible thanks to ATDC’s support. They helped SON fundraise by finding the right sponsors.

“We went from starting this convention in a pizza shop to now packing an entire plaza downtown,” Clarke said. “To see the growth is amazing. We've received a lot of industry backing because of the creative ways we're helping workforce development.”

Dike wants to ensure the event wasn’t a one-off and that SON can keep up the momentum. SON is already planning an even bigger 2026 Isekai convention, with exciting new partners in the pipeline who want to share in the energy of this creative workforce development solution and movement.

SON also announced a partnership with gaming company Blaze Fire Games and the Houston County School District. The school district can access Blaze Fire Games’ Recruit, Reclaim, and Retain career pathway program, which is designed to help close the technology industry’s vast talent gap.

“The partnership is exciting because it represents more than creating and launching an esports club,” said Isiah Reese, CEO and co-founder of Blaze Fire Games. “This agreement allows our company to continue creating opportunities and develop relevant, sustainable career-readiness skills required to compete in today’s environment.”

Sherri Johnson, the CEO and principal of Houston County College and Career Academy, agrees. "The partnership is a real game-changer for our students. These unique, forward-thinking, 21st-century digital economy workforce educational courses will empower our instructors to reimagine and enhance classroom learning within our cybersecurity and gaming career pathway programs.”

SON is ready to rise to whatever industry or challenge needs their model next. What they have been able to do for the IT and cybersecurity fields could eventually be applied to the Federal Aviation Administration or even healthcare technician jobs. There’s an entirely new way to develop the tech world field, and it may not start in a classroom but with a controller.

Georgia Tech roboticists are attempting to identify the most stressful periods that human teleoperators experience while performing tasks remotely. A novel study provides new insights into determining when a teleoperator needs to operate at a high level of focus and which parts of the task can be delegated to robot automation.

School of Interactive Computing Associate Professor Matthew Gombolay calls it the “sweet spot” of human ingenuity and robotic precision. Gombolay and students from his CORE Robotics Labconducted a novel study that measures stress and workload on human teleoperators.

Gombolay said it can inform military officials on how to strategically implement task automation and maximize human teleoperator performance.

Humans continue to hand over more tasks to robots to perform, but Gombolay said that some functions will still require human input and oversight for the foreseeable future.

Specific applications, such as space exploration, commercial and military aviation, disaster relief, and search and rescue, pose substantial safety concerns. Astronauts stationed on the International Space Station, for example, manually control robots that bring in supplies, move cargo, and make structural repairs.

“It’s brutal from a psychological perspective,” Gombolay said.

The question often asked about automating a task in these fields is, at what point can a robot be trusted more than a human?

A recent paper by Gombolay and his current and former students — Sam Yi Ting, Erin Hedlund-Botti, and Manisha Natarajan — sheds new light on the debate. The paper was published in the IEEE Robotics and Automation Letters and will be presented at the International Conference on Robotics and Automation in Atlanta.

The NASA-funded study can identify which aspects of tedious, time-consuming tasks can be automated and which require human supervision. If roboticists can pinpoint the elements of a task that cause the least stress, they can automate these components and enable humans to oversee the more challenging aspects.

“If we’re talking about repetitive tasks, robots do better with that, so if you can automate it, you should,” said Ting, a former grad student and lead author of the paper. “I don’t think humans enjoy doing repetitive tasks. We can move toward a better future with automation.”

Military officials, for example, could measure the stress of remote drone pilots and know which times during a pilot’s shift require the highest level of attention.

“We can get a sense of how stressed you are and create models of how divided your attention is and the performance rate of the tasks you’re doing,” Gombolay said.

“It can be a low-stress or high-stress situation depending on the stakes and what’s going on with you personally. Are you well-caffeinated? Well-rested? Is there stress from home you’re bringing with you to the workplace? The goal is to predict how good your task performance will be. If it indicates it might be poor, we may need to outsource work to other people or create a safe space for the operator to destress.”

The Stress Test

For their study, the researchers cut a small river-shaped path into a medium-density fiberboard. The exercise required the 24 participants to use a remote robotic arm to navigate through the path from one end to the other without touching the edges.

The experiment grew more challenging as new stress conditions and workload requirements were introduced. The changing conditions required the test participants to multitask to complete the assignment.

Gombolay said the study supports the Yerkes-Dodson Law, which states that moderate levels of stress increase human performance.

The experiment showed that operators felt overwhelmed and performed poorly when multitasking was introduced. Too much stress led to poor performance, but a moderate amount of stress induced more engagement and enhanced teleoperator focus. 

Ting said finding that ideal stress zone can lead to a higher performance rating. 

“You would think the more stressed you are, the more your performance decreases,” Ting said. “Most people didn’t react that way. As stress increased, performance increased, but when you increased workload and gave them more to do, that’s when you started seeing deteriorating performance.”

Gombolay said no stress can be just as detrimental as too much stress. Performing a task without stress tends to cause teleoperators to become disinterested, especially if it is repetitive and time-consuming.

“No stress led to complacency,” Gombolay said. “They weren’t as engaged in completing the task.

“If your excitement is too low, you get so bored you can’t muster the cognitive energy to reason about robot operation problems.”

The Human Factor

Roboticists have made significant leaps in recent years to remove teleoperators from the equation. Still, Gombolay said it’s too early to tell whether robots can be trusted with any task that a human can perform.

“We’re a long way from full autonomy,” he said. “There’s a lot that robots still can’t do without a human operator. Search and rescue operations, if a building collapses, we don’t have much training data for robots to go through rubble by themselves to rescue people. There are ethical needs for humans to be able to supervise or take direct control of robots.”

In November 2024, JSC granted Assistant Professor Spencer Bryngelson exclusive access to the system through the JUPITER Research and Early Access Program (JUREAP).

By preparing Europe’s fastest supercomputer for launch, the joint project yielded valuable simulation data on the effects of shock waves in medicine and transportation.

“The shock-droplet problem has been a hallmark test problem in fluid dynamics for some decades now. It is sufficiently challenging to study that it keeps me scientifically interested, though the results are manifestly important,” Bryngelson said. 

“Understanding the droplet behavior in some extreme regimes remains an open scientific problem of high engineering value.”

Through JUREAP, JSC engineers tested Bryngelson’s Multi-Component Flow Code (MFC) on their computers. The project simulated how liquid droplets behave when struck by a large, high-velocity shock wave moving much faster than the speed of sound.

Tests produced visualizations of droplets deforming into pancake shapes before ejecting vortex rings as they broke apart from the shock wave. The experiments measured the swirls of air flow formed behind the droplets, known as vorticity.

Vorticity is one variable aerospace engineers consider when building aircraft designed to fly at supersonic and hypersonic speeds. Small droplets and vortices pose significant hazards for high-Mach vessels.

These computer models reduce the risk and cost associated with physical test runs. By simulating extreme scenarios, the JUREAP project demonstrated a safer and more efficient way to evaluate aerospace systems.

The human body is another fluid space where fast, high-energy flows can occur.

Simulations help medical researchers create less invasive shock wave treatments. This technology can be further applied for uses ranging from breaking up kidney stones to treating inflammation. 

MFC’s versatility for large- and small-scale applications made it suitable for testing JUPITER in its early stages. The project’s success even earned it a JUREAP certificate for scaling efficiency and node performance.

“The use of application codes to test supercomputers is common. We’ve participated in similar programs for OLCF Frontier and LLNL El Capitan,” said Bryngelson, a faculty member with Georgia Tech’s School of Computational Science and Engineering.

“Engineers at supercomputer sites usually find and sort most problems on their own. But deploying workloads characteristic of what the JUPITER will run in practice stresses it in new ways. In these instances, we usually end up identifying some failure modes.”

The JSC and Georgia Tech researchers named their joint project Exascale Multiphysics Flows (ExaMFlow).

ExaMFlow helps keep JUPITER on pace to become Europe’s first exascale supercomputer. This designation refers to any machine capable of computing one exaflop, or one quintillion (“1” followed by 18 zeros) calculations per second. 

All three systems that rank ahead of JUPITER are exascale supercomputers. They are El Capitan at Lawrence Livermore National Laboratory, Frontier at Oak Ridge National Laboratory, and Aurora at Argonne National Laboratory. 

JUPITER calculates more than 60 billion operations per watt. This makes the supercomputer the most energy-efficient system among the top five. 

ExaMFlow ran Bryngelson’s software on JSC’s JUWELS Booster and JUPITER Exascale Transition Instrument (JETI). The two modules form the backbone of JUPITER’s full design.

ExaMFlow’s report showed that MFC performed with near-ideal scaling behavior on JUWELS and JETI compared to similar systems based on NVIDIA A100 GPUs.

Access to NVIDIA hardware at Georgia Tech played a key role in ExaMFlow’s success.

The Institute hosts the Phoenix Research Computing Cluster, which includes A100 GPUs among its arsenal of components. Bryngelson’s lab owns NVIDIA A100 GPUs and four GH200 Grace Hopper Superchips. 

Since JUPITER is equipped with around 24,000 Grace Hopper Superchips, Bryngelson’s work with the hardware proved especially insightful for the ExaMFlow project.   

“The Grace Hopper chip is interesting. It’s not challenging to use like a regular GPU device when one is familiar with running NVIDIA hardware. The more fun part is using its tightly coupled CPU to GPU interconnect to make use of the CPU as well,” Bryngelson said. 

“It’s not immediately obvious how to best do this, though we used a few tricks to tune its use to our application. They appear to work nicely.”

JSC researchers Luis Cifuentes, Rakesh Sarma, Seong Koh, and Sohel Herff played important roles in running Bryngelson’s MFC software on early JUPITER modules. 

The ExaMFlow team included NVIDIA scientists Nikolaos Tselepidis and Benedikt Dorschner. 

The pair observed their company’s hardware used in the field. They return to NVIDIA with notes that help the corporation build the next devices tailored to the need of scientific computing researchers. 

“We try to be prepared for the latest, biggest computers. Being able to take immediate advantage of the largest systems is a valuable capability,” Bryngelson said. 

“When the early access systems arrive, it’s a great opportunity for the teams involved to test the machines, demonstrate and tune scientific software, and meet very capable new collaborators.”

The study, “TopoNets: High-Performing Vision and Language Models With Brain-Like Topography,” was awarded a spotlight at this year’s International Conference on Learning Representations (ICLR), a distinction given to only 2 percent of papers. The research was led by graduate student Mayukh Deb alongside School of Psychology Assistant Professor Apurva Ratan Murty.

Thirty-two of Tech’s computing, engineering, and science faculty represented the Institute at ICLR 2025, which is globally renowned for sharing cutting-edge research. 

“We started with this idea because we saw that AI models are unstructured, while brains are exquisitely organized,” says first-author Deb. “Our models with internal structure showed more than a 20 percent boost in efficiency with almost no performance losses. And this is out-of-the-box — it’s broadly applicable to other models with no extra fine-tuning needed.”

For Murty, the research also underscores the importance of a rapidly growing field of research at the intersection of neuroscience and AI. “There's a major explosion in understanding intelligence right now,” he says. “The neuro-AI approach is exciting because it helps emulate human intelligence in machines, making AI more interpretable.”

“In addition to advancing AI, this type of research also benefits neuroscience because it informs a fundamental question: Why is our brain organized the way it is?,” Deb adds. “Making AI more interpretable helps everyone.”

Brain-inspired blueprints

In the brain, neurons form topographic maps: neurons used for comparable tasks are closer together. The researchers applied this concept to AI by organizing how internal components (like artificial neurons) connect and process information. 

This type of organization has been tried in the past but has been challenging, Murty says. “Historically, rules constraining how the AI could structure itself often resulted in lower-performing models. We realized that for this type of biophysical constraint, you simply can’t map everything — you need an algorithmic solution.”

“Our key insight was an algorithmic trick that gives the same structure as brains without enforcing things that models don't respond well to,” he adds. “That breakthrough was what Mayukh (Deb) worked on.” 

The algorithm, called TopoLoss, uses a loss function to encourage brain-like organization in artificial neural networks, and it is compatible with many AI systems capable of understanding language and images. 

“The resulting training method, TopoNets, is very flexible and broadly applicable,” Murty says. “You can apply it to contemporary models very easily, which is a critical advancement when compared to previous methods.” 

Neuro-AI innovations

Murty and Deb plan to continue refining and designing brain-inspired AI systems. “All parts of the brain have some organization — we want to expand into other domains,” Deb says. “On the neuroscience side of things, we want to discover new kinds of organization in brains using these topographic systems.”

Deb also cites possibilities in robotics, especially in situations like space exploration where resources are limited. “Imagine running a model inside a robot with limited power,” he says. “Structured models can help us achieve 80 percent of performance with just 20 percent of energy consumption, saving valuable energy and space. This is still experimental, but it's the direction we are interested in exploring.”

“This success highlights the potential of a new approach, designing systems that benefit both neuroscience and AI — and beyond,” Murty adds. “We can learn so much from the human brain, and this project shows that brain-inspired systems can help current AI be better. We hope our work stimulates this conversation.”

Top South Korean research institutes have enlisted Georgia Tech researchers Sehoon Ha and Jennifer G. Kim to develop artificial intelligence (AI) to help the humanoid assistant navigate hospitals and interact with doctors, nurses, and patients.

Ha and Kim will partner with Neuromeka, a South Korean robotics company, on a five-year, 10 billion won (about $7.2 million US) grant from the South Korean government. Georgia Tech will receive about $1.8 million of the grant.

Ha and Kim, assistant professors in the School of Interactive Computing, will lead Tech’s efforts and also work with researchers from the Korea Advanced Institute of Science and Technology and the Electronics and Telecommunications Research Institute.

Neuromeka has built industrial robots since its founding in 2013 and recently decided to expand into humanoid service robots.

Lee, the group leader of the humanoid medical assistant project, said he fielded partnership requests from many academic researchers. Ha and Kim stood out as an ideal match because of their robotics, AI, and human-computer interaction expertise. 

For Ha, the project is an opportunity to test navigation and control algorithms he’s developed through research that earned him the National Science Foundation CAREER Award. Ha combines computer simulation and real-world training data to make robots more deployable in high-stress, chaotic environments. 

“Dr. Ha has everything we want to put into our system, including his navigation policies,” Lee said. “He works with robots and AI, and there weren’t many candidates in that space. We needed a collaborator who can create the software and has experience running it on robots.”

Ha said he is already considering how his algorithms could scale beyond hospitals and become a universal means of robot navigation in unstructured real-world environments.

“For now, we’re focusing on a customized navigation model for Korean environments, but there are ways to transfer the data set to different environments, such as the U.S. or European healthcare systems,” Ha said. 

“The final product can be deployed to other systems and industries. It can help industrial workers at factories, retail stores, any place where workers can get overwhelmed by a high volume of tasks.”

Kim will focus on making the robot’s design and interaction features more human. She’ll develop a large-language model (LLM) AI system to communicate with patients, nurses, and doctors. She’ll also develop an app that will allow users to input their commands and queries. 

“This project is not just about controlling robots, which is why Dr. Kim’s expertise in human-computer interaction design through natural language was essential.,” Lee said. 

Kim is interviewing stakeholders from three South Korean hospitals to identify service and care pain points. The issues she’s identified so far relate to doctor-patient communication, a lack of emotional support for patients, and an excessive number of small tasks that consume nurses’ time.

“Our goal is to develop this robot in a very human-centered way,” she said. “One way is to give patients a way to communicate about the quality of their care and how the robot can support their emotional well-being.

“We found that patients often hesitate to ask busy nurses for small things like getting a cup of water. We believe this is an area a robot can support.”

The robot’s hardware will be built in Korea, while Ha and Kim will develop the software in the U.S.

Jong-hoon Park, CEO of Neuromeka, said in a press release the goal is to have a commercialized product as soon as possible. 

“Through this project, we will solve problems that existing collaborative robots could not,” Park said. “We expect the medical AI humanoid robot technology being developed will contribute to reducing the daily work burden of medical and healthcare workers in the field.”

Meta announced in February its partnership with the labs of professors Danfei Xu and Judy Hoffman on a novel computer vision-based algorithm called EgoMimic. It enables robots to learn new skills by imitating human tasks from first-person video footage captured by Meta’s Aria smart glasses. 

Xu’s Robot Learning and Reasoning Lab (RL2) displayed EgoMimic in action at ICRA May 19-23 at the World Congress Center in Atlanta.

Lawrence Zhu, Pranav Kuppili, and Patcharapong “Elmo” Aphiwetsa — students from Xu’s lab — used Egomimic to compete in a robot teleoperation contest at ICRA. The team finished second in the event titled What Bimanual Teleoperation and Learning from Demonstration Can Do Today, earning a $10,000 cash prize.

Teams were challenged to perform tasks by remotely controlling a robot gripper. The robot had to fold a tablecloth, open a vacuum-sealed container, place an object into the container, and then reseal it in succession without any errors.

Teams completed the tasks as many times as possible in 30 minutes, earning points for each successful attempt.

The competition also offered different challenge levels that increased the points awarded. Teams could directly operate the robot with a full workstation view and receive one point for each task completion. Or, as the RL2 team chose, teams could opt for the second challenge level.

The second level required an operator to control the task with no view of the workstation except for what was provided to through a video feed. The RL2 team completed the task seven times and received double points for the challenge level.

The third challenge level required teams to operate remotely from another location. At this level, teams could earn four times the number of points for each successful task completed. The fourth level challenged teams to deploy an algorithm for task performance and awarded eight points for each completion.

Using two of Meta’s Quest wireless controllers, Zhu controlled the robot under the direction of Aphiwetsa, while Kuppili monitored the coding from his laptop.

“It’s physically difficult to teleoperate for half an hour,” Zhu said. “My hands were shaking from holding the controllers in the air for that long.”

Being in constant communication with Aphiwetsa helped him stay focused throughout the contest.

“I helped him strategize the teleoperation and noticed he could skip some of the steps in the folding,” Aphiwetsa said. “There were many ways to do it, so I just told him what he could fix and how to do it faster.”

Zhu said he and his team had intended to tackle the fourth challenge level with the EgoMimic algorithm. However, due to unexpected time constraints, they decided to switch to the second level the day before the competition due to unexpected time constraints. 

“I think we realized the day before the competition training the robot on our model would take a huge amount of time,” Zhu said. “We decided to go for the teleoperation and started practicing.”

He said the team wants to tackle the highest challenge level and use a training model for next year’s ICRA competition in Vienna, Austria.

ICRA is the world’s largest robotics conference, and Atlanta hosted the event for the third time in its history, drawing a record-breaking attendance of over 7,000.

She said the police officer who interviewed her was dismissive and neglected to write down details that Foriest found significant. The deficient police report was picked up by local media, which led to news stories that inaccurately described the crime and left out important information.

Foriest said she learned from the incident that incomplete information doesn’t mitigate violence. The perspectives and stories of people who experience violence are essential to reliable data.

The incident guided Foriest as she committed to research that gathers complete and accurate data on multiple types of violence, including violent injury and homicide, intimate partner violence, gender-based violence, and suicide.

Foriest earned a bachelor’s in health science from Columbus State University. She also holds two master’s degrees: one in public health from the University of Southern California, and another in technology leadership and management from Agnes Scott College.

In 2021, Foriest started her Ph.D. in human-centered computing at Georgia Tech to understand how technology influences violence.

“I look at all types of violence as an outcome of how technology affects communication,” she said. 

One thing she discovered was that even though technology can amplify victims’ voices, it is often used to silence them.

“The same social dynamics that keep people from disclosing their violent experiences to formal reporting sources offline also happen online,” she said.

Bringing the Cardiff Model to the U.S.

Before arriving at Tech, Foriest worked for eight years as an injury prevention coordinator at Grady Memorial Hospital in Atlanta. She implemented a trauma recovery center and Atlanta’s first hospital-based violence intervention program.

While in that position, she worked with the Cardiff Model for Violence Prevention, a public health approach to violence prevention developed by researchers at Cardiff University in Wales.

The Cardiff model’s philosophy is that violence prevention is best achieved when the healthcare and law enforcement sectors combine geographical data to determine where violence occurs in a community. 

“The Cardiff model taught Wales there was a lot about violence they didn’t know from police data alone,” Foriest said. 

One example is that researchers learned an alarming number of hospital patients were brought in from local taverns. This finding informed policymakers to implement new regulations, such as changing licensing requirements and serving alcohol in toughened glasses or non-glass vessels so they can’t be used as weapons.

In 2011, the city of Cardiff reported a 42% reduction in hospital admissions for hospital injuries. It wasn’t long before the researchers in the U.S. began importing the Cardiff model. In 2018, it became an official policy of the Centers for Disease Control and Prevention (CDC). 

The U.S. Department of Justice found in 2022 that 58% of violent crimes were not reported to law enforcement. Sixteen cities that make up the Cardiff Model for Violence Prevention National Networkare now gathering and mapping patient-reported violent injury data from hospitals to fill that data gap. 

Atlanta is one of the cities in that network, and Foriest has been an on-the-ground researcher collecting that data. Her work with the Cardiff model seamlessly integrated into her Ph.D. research as she sought ways to turn technology into a safe avenue of violence disclosure.

Working with Alex Godwin, a former Ph.D. student at Georgia Tech who is now an assistant professor at American University, she helped develop a user interface and mapping algorithm. The tool allows hospital patients who are violence victims to identify the location of the violent incident they experienced.

Foriest said, “Around the Covid-19 pandemic, we had challenges getting patients screened, and we thought we should explore different options.

“Our interface allows patients to tap down to the degree they’re comfortable on the geographic location where they were injured.

“It improved our ability to map data tremendously and decreased some of the risks patients face when disclosing violence.”

Foriest and Godwin's paper on the development of the interface tool earned an honorable mention for best paper at the 2025 Conference on Human Factors in Computing Systems (CHI) in Yokohama, Japan.

Foriest also co-authored an award-winning paper at the 2024 Conference on Computer-Supported Cooperative Work (CSCW). That paper examined how social media often silences violence victims.

Foriest is also a fellow for Data Science and Innovation at the CDC, where she continues her work on the Cardiff model. She also examines how news media coverage of suicides can often reinforce stigmas about the causes of suicide in that role.

Thriving at Tech

Foriest is entering her fifth year as a Ph.D. student, but before she came to Tech, she had no computing experience. She applied to numerous Ph.D. programs but was eventually persuaded that technology could complement her public health expertise and her goal of preventing violence.

“Tech was the only place where I could gain a new skill set while doing the things that I wanted to do in research,” she said. 

“That felt like the best fit for me, where I would get the most out of my training. I was encouraged by faculty and my peers to recognize that my perspective is valuable, and I can speak from that place and bridge my knowledge with HCI concepts.”

We caught up with Holly and Andrew to learn more about what makes Georgia Tech so appealing to students and employees alike, and the unique perspective their mother-son relationship brings to campus. 

How long have you worked at Georgia Tech? What do you do as a financial operations assistant director?

[Holly] I have been at Georgia Tech since 2000 and joined the College of Computing in early 2005. Ironically and very memorably, I found out I was expecting Andrew right after I started in Computing. I still recall being very nervous about telling my new boss that I was expecting, but she was happy for me and very accommodating. I went to the bookstore right after our meeting and bought Andrew his first Georgia Tech t-shirt, which I plan to pass down to him one day. 

Being part of the College for this long, I have watched it grow from having divisions to schools. I began as a financial administrator and steadily grew into my current role as assistant director of financial operations for the School of Computational Science and Engineering (CSE). In my current role, I oversee financial operations for the School of CSE, including budgeting, forecasting, financial reporting, and ensuring compliance with Institute and sponsor guidelines. I work closely with faculty, staff, and leadership to support our financial programs and other initiatives. It is a rewarding role that allows me to contribute to the success of the college while watching it grow, just like my own journey here. 

How much influence did your mom’s work at Georgia Tech have on your interest in coming here for college?

[Andrew] It definitely played a role. I grew up a fan of all things Georgia Tech, so this was always my dream school. When I got in, all the stars aligned. Tech was my dream school, my mom worked there, and I was close to home. It was perfect.  

What is it about Georgia Tech that has kept you here for more than two decades?

[Holly] From the beginning, I have always felt that my work contributes to something bigger – supporting faculty who offer world-class education and innovation. I have had the opportunity to grow professionally and work alongside very talented colleagues. 

How has your first year gone? What do you like best about attending Georgia Tech?

[Andrew] Overwhelming. I wasn’t sure what to expect from attending college. The college lifestyle was a big change for me, and I had to learn how to navigate it. I knew Georgia Tech would be challenging, and I thought I was ready for it, but it was still harder than I expected. However, I managed to get through my first year with great resilience and finish stronger than I started.  

What do you each like best about being on campus together?

[Holly] I enjoy being nearby and getting to share this chapter of his life. There are many times that Andrew is focused on his studies or his fraternity commitments, so he doesn’t get to come home as often as I would like. But with me being on campus, we can grab a quick lunch or have a short visit. I also like knowing he is a short walk from my office if I want to drop off a homemade meal. Even when we are both too busy for a visit, sometimes I find myself looking out the window across campus. Just seeing the top of a building where he is attending class gives me comfort knowing he is there.

[Andrew] Bouncing off of what my mom said, it has been great. It is comforting that I can go to her office just to say “hey,” and not drive all the way home. It’s nice that when I’m having a rough patch with school, she drops by to offer some reassurance.

What has been the key to reaching the milestones of a fulfilling career and witnessing your children achieve their goals?

[Holly] The key to reaching these milestones has really been maintaining a healthy work-life balance. Georgia Tech has given me the space and support to grow professionally while also being present as a parent. That balance has been everything. It allowed me to build a fulfilling career that I’m proud of, while also being there to watch my children grow and pursue their dreams, including Andrew becoming a Georgia Tech student himself. Being able to do both, without having to choose one over the other, has truly been the foundation of my success and happiness.  

What do you look forward to in the next few years studying computer engineering at Georgia Tech? And after graduating?

[Andrew] I am most excited for my threads and starting my career. I have learned so much that I am already applying my studies. I recently used Raspberry Pi to build a circuit that enabled a motion detector to work and set off an LED indicating motion. This was a part of my discovery class for my major, and it was the most fun I have had at Georgia Tech so far. It was very new and exciting to learn about, and it motivates me to put my skills to work.

After graduating, I want to work in cybersecurity, possibly as a hardware security engineer for the government or even my own startup. The project I mentioned opened my eyes to my threads and really motivated me to continue in this field. 

Rush is one of more than 150 College of Computing staff members who support the College and its five schools. Staff members are the backbone of the College. From managing operations to providing essential services, their dedication ensures the seamless delivery of education, research, and community support, making them integral to the College's success.

It may not be long before augmented reality/virtual reality (AR/VR) headsets cause them to keep their phones in their pockets when they want to read The New York Times or The Washington Post.

Data visualization and AR/VR researchers at Georgia Tech are exploring how users can interact with news stories through AR/VR headsets and are determining which stories are best suited for virtual presentation.

Tao Lu, a Ph.D. student at the School of Interactive Computing, Assistant Professor Yalong Yang, and Associate Professor Alex Endert led a recent study that they say is among the first to explore user preference in virtually designed news stories.

The researchers will present a paper they authored based on the study at the 2025 Conference on Human Factors in Computing Systems this week in Yokohama, Japan.

Digital platforms have elevated explanatory journalism, which provides greater context for a subject through data, images, and in-depth analysis. These platforms also allow stories to be more visually appealing through graphic design and animation. 

Lu said AR/VR can further elevate explanatory journalism through 3D, interactive spatial environments. He added that media organizations should think about how the stories they produce will appear in AR/VR as much as they think about how they will appear on mobile devices.

“We’re giving users another option to experience the story and for designers and developers to show their stories in another modality,” Lu said.

“A screen-based story on a smartphone is easy to use and cost-effective. However, some stories are better presented in AR/VR, which will become more popular as technology gets cheaper. AR/VR can provide 3D spatial information that would be hard to understand on a phone or desktop screen.”

Active or Passive Interactions?

Using Meta’s Oculus Quest 3, the researchers and their collaborators created four immersive virtual reality simulations from web-based news stories produced by The New York Times:

• Why opening windows was key to classroom ventilation during the Covid-19 pandemic
• The destruction of Black homes and businesses in the Tulsa Race Massacre
• How climate change could create dramatic dangers in the Atlantic Ocean
• How 9/11 changed Manhattan’s financial district

The study aimed to determine whether users prefer to be actively or passively immersed in a story, whether from a first-person or third-person point of view, or a combination of these perspectives.

“We’re in the nascent stages of storytelling in VR,” said Endert, whose research specializes in data visualization. “We lack the design knowledge of which mode of immersion we should use if we want a certain reaction from the audience. Understanding design is at the crux of our study.”

Active immersion gives the user complete control over their experience. The classroom simulation offers a first-person point of view and allows users to teleport from one point in the classroom to another. New information from the story is presented each time the user moves to a new point. 

The researchers acknowledged they could design a free-roaming simulation that allows users to walk freely within the classroom. However, they restricted that ability for this study due to safety concerns and lab space constraints. 

In the Tulsa Race Massacre simulation, which uses a passive, first-person point of view, users follow a predefined route along one of Tulsa’s main streets. Information about each building is presented at each step.

The Atlantic Ocean simulation is an active, third-person experience. The user sees a representation of Earth and can select which interaction points to explore to learn new information.

The 9/11 simulation is a passive third-person experience. Each step includes a narrative paragraph with companion visual elements, and users proceed to the next step through a navigation trigger.

Finding the Right Balance

Lu said that first-person active enhances spatial awareness, while third-person passive improves contextual understanding. Journalists and VR designers must determine which presentation is most effective case by case.

Yang said the goal should be to balance interests in making those determinations, which might require compromise. Knowing how users prefer to consume news is critical, but journalists still have an editorial responsibility to decide what the public should know and how to present information.

“You have more freedom to explore in an active experience versus a passive experience,” Yang said. “But if you give them too much freedom, they might stray from your planned narrative and miss important information you think they should know. We want to understand how we can balance both ends of this spectrum and what the right level is that we can give people in storytelling.”

The study and others indicate that users retain information better when they feel like they are part of the story. Yang said the technology to make that possible isn’t there yet, but it’s coming along as wearable VR devices become more accessible.

The debate is whether these devices will become people's preferred technology for consuming content. According to the Pew Research Center, 86% of U.S. adults say they at least sometimes get their news from a smartphone, computer, or tablet.

“I believe AR and VR will be mainstream in the future and will replace everything, but I think there’s a transition period,” Yang said. “Older devices will exist and act as support. It’s an ecosystem.”

The crowd grew so large that no one could move in the alley, resulting in the deadliest crowd crush in the nation’s history. Nearly 160 people were killed, and another 196 were injured.

Soonho Kwon, a first-year human-centered computing Ph.D. student at Georgia Tech, lived within walking distance of the alley when the incident occurred.

“It was tragic,” Kwon said. “It really makes you think about how life is fragile. Everyone in my community talked about what it would have been like if they were in that alleyway.”

Many of the victims were young people — some of them teens who had no identification on them. Kwon thought about their family members being told their loved ones’ lives had been cut short. He wondered what memories those families would have of the deceased.

The incident inspired Kwon to create a new mobile platform that helps young adults and career professionals create a post-death memorial for their families. The platform, which Kwon and his research collaborators named Timeless, allows users to be remembered how they want to be remembered in the event of their untimely death.

“Most death preparation services are for terminally ill patients or aging adults, focusing on will management or funeral planning,” Kwon said. “We thought such needs may differ for young adults and asked how we could design a system that better caters to their needs.”

Timeless is a photo-based death preparation system that enables users to send a physical package containing pre-curated pictures, voice recordings, and letters to a designated recipient in the event of their passing. 

The system syncs with a user’s mobile photo album and creates a list of scanned faces. Users can select a face and view all the photos they’ve taken with that person. They can choose which photos they want sent to that person after death and write individual messages for each image.

Once the user’s death has been reported, Timeless sends a package to each selected individual with printed photos, letters, and a QR code or a CD that contains videos or voice recordings.

Breaking the Ice

Kwon and his collaborators designed Timeless based on a group study that asked participants to imagine what would happen if they unexpectedly died. The participants were asked what was on their bucket lists, their epitaphs, and what they would wish for if they could make one wish come true.

“Surprisingly, people were happy to participate because we framed it in a way that wasn’t gloomy,” Kwon said. “Many shared that reflecting on their death motivated them to actively express their love and be grateful for what they have. Turning something as heavy as death into something positive was a key design implication.”

Digital vs. Physical

Kwon began his research career examining virtual commemoration systems, including Facebook and Instagram commemoration pages, during the Covid-19 pandemic and exploring how technology can meaningfully memorialize the deceased.

He said two aspects distinguish Timeless from other commemoration platforms: 

• The deceased can decide how and by whom they want to be remembered.
• The fusion of digital memorialization with physical memorialization

“Leveraging only the digital side of it can be superficial,” Kwon said. “We build monuments, statues, and tombstones because the notion of death itself is losing your physical presence. By making it physical, we aimed to connect the discussion on digital legacies to traditional human commemoration forms.”

AI Afterlife

Kwon also said he is aware of artificial intelligence (AI) afterlife. This emerging technology allows people to train an AI agent and produce digital avatars with which family and friends can communicate after they die.

Meredith Ringel Morris, director and principal scientist for human-AI interaction at Google DeepMind, spoke about AI afterlife in October during the Summit on AI, Responsible Computing, and Society hosted by Georgia Tech’s School of Interactive Computing.

In her talk, Morris spoke about the criticism AI afterlife is already facing for causing people to experience extended grief and the inability to move on from losing a loved one.

Kwon said another drawback is that AI agents are susceptible to hallucinations and could say untrue things about the deceased. 

“How can you say for sure that the representation of AI is me?” he said. “As researchers, our role is to explore and critically examine how the emergence of such technology may shape society while striving to ensure its development benefits people.” 

Kwon sees Timeless as a catalyst for meaningful discussions about how a digital legacy curation system may accurately reflect a user’s wishes before death. 

He will present a paper on Timeless's design process and its implications at the 2025 ACM Conference on Human Factors in Computing Systems (CHI) this week in Yokohama, Japan.

Ph.D. candidate Md Abdur Rahaman’s dissertation studies brain data to understand how changes in brain activity shape behavior. 

Computational tools Rahaman developed for his dissertation look for informative patterns between the brain and behavior. Successful tests of his algorithms show promise to help doctors diagnose mental health disorders and design individualized treatment plans for patients.

“I've always been fascinated by the human brain and how it defines who we are,” Rahaman said. 

“The fact that so many people silently suffer from neuropsychiatric disorders, while our understanding of the brain remains limited, inspired me to develop tools that bring greater clarity to this complexity and offer hope through more compassionate, data-driven care.”

Rahaman’s dissertation introduces a framework focusing on granular factoring. This computing technique stratifies brain data into smaller, localized subgroups, making it easier for computers and researchers to study data and find meaningful patterns.

Granular factoring overcomes the challenges of size and heterogeneity in neurological data science. Brain data is obtained from neuroimaging, genomics, behavioral datasets, and other sources. The large size of each source makes it a challenge to study them individually, let alone analyze them simultaneously, to find hidden inferences. 

Rahaman’s research allows researchers and physicians to move past one-size-fits-all approaches. Instead of manually reviewing tests and scans, algorithms look for patterns and biomarkers in the subgroups that otherwise go undetected, especially ones that indicate neuropsychiatric disorders.

“My dissertation advances the frontiers of computational neuroscience by introducing scalable and interpretable models that navigate brain heterogeneity to reveal how neural dynamics shape behavior,” Rahaman said. 

“By uncovering subgroup-specific patterns, this work opens new directions for understanding brain function and enables more precise, personalized approaches to mental health care.”

Rahaman defended his dissertation on April 14, the final step in completing his Ph.D. in computational science and engineering. He will graduate on May 1 at Georgia Tech’s Ph.D. Commencement. 

After walking across the stage at McCamish Pavilion, Rahaman’s next step in his career is to go to Amazon, where he will work in the generative artificial intelligence (AI) field. 

Graduating from Georgia Tech is the summit of an educational trek spanning over a decade. Rahaman hails from Bangladesh where he graduated from Chittagong University of Engineering and Technology in 2013. He attained his master’s from the University of New Mexico in 2019 before starting at Georgia Tech. 

“Munna is an amazingly creative researcher,” said Vince Calhoun, Rahman’s advisor. Calhoun is the founding director of the Translational Research in Neuroimaging and Data Science Center (TReNDS).

TReNDS is a tri-institutional center spanning Georgia Tech, Georgia State University, and Emory University that develops analytic approaches and neuroinformatic tools. The center aims to translate the approaches into biomarkers that address areas of brain health and disease.    

“His work is moving the needle in our ability to leverage multiple sources of complex biological data to improve understanding of neuropsychiatric disorders that have a huge impact on an individual’s livelihood,” said Calhoun.

The Society for Industrial and Applied Mathematics (SIAM) selected Elizabeth Cherry and Katya Scheinberg as Class of 2025 fellows. The two Georgia Tech faculty join an illustrious class of 23 other researchers from around the globe in this year’s class. 

SIAM selected Cherry to recognize her contributions to mathematical and computational modeling and extensive service to the SIAM community. She studies the electrical behavior of cardiac cells and tissue.

Cherry’s computer models and simulations improve understanding of cardiac dynamics in normal and diseased states. Using these tools, she designs advanced strategies for preventing and treating arrhythmias.

“SIAM has played a huge role in my professional development—the first conference I attended as a graduate student was a SIAM conference, and I’ve attended at least one SIAM conference almost every year since then,” Cherry said. 

“Given this long history, it means a lot to me for SIAM to acknowledge my contributions in this way.”

Scheinberg, from Georgia Tech’s College of Engineering, was selected for her foundational contributions to derivative-free optimization and optimization applications in data science and her dedicated service to the optimization community.

[Related: Coca-Cola Foundation Chair Katya Scheinberg selected for 2025 Class of SIAM Fellows]

Cherry is the fifth faculty member from the School of Computational Science and Engineering (CSE) to be selected as a SIAM Fellow.

Cherry’s announcement as a SIAM Fellow comes weeks after serving in a leadership role at a SIAM conference. She co-chaired the organizing committee of the SIAM Conference on Computational Science and Engineering (CSE25).

In 2023, SIAM members reelected Cherry to a second term as a council member-at-large. She began her three-year term in January 2024.

"SIAM Fellows are selected for deep mathematical contributions. Receiving Fellow status is a high honor for any applied mathematician," said Regents’ Professor Srinivas Aluru, senior associate dean of the College of Computing and Class of 2020 SIAM Fellow. 

"Not only are Elizabeth's contributions technically outstanding, but her work also provides deep insights into the functioning of the heart and its abnormalities."

Cherry’s leadership and service extends outside of SIAM, influencing students and faculty across Georgia Tech. 

In December, the College of Computing appointed Cherry as associate dean for graduate education. Before this appointment, she served as associate chair for academic affairs of the School of CSE. 

With her new role as associate dean, Cherry continues serving as director of CSE programs at Georgia Tech. 

In March 2024, Cherry was among five Georgia Tech faculty members selected for the ACC Academic Leaders Network (ACC ALN) Fellows program. The ALN program fosters cross-institutional networking and collaboration between ACC schools, increasing each institution’s academic leadership capacity.

Cherry was part of a team of Georgia Tech and Emory University researchers who won a Georgia Clinical and Translational Science Alliance award in 2023. The group earned the Team Science Award of Distinction for Early Stage Research Teams award for work that captures high-resolution visualizations of spiral waves that create heart arrhythmias.

SIAM will recognize Cherry, Scheinberg, and Class of 2025 fellows during a reception at the SIAM/CAIMS Annual Meetings this July in Montréal.

“It is such an honor to be recognized as a SIAM Fellow,” Cherry said. “I’m thrilled to join my CSE colleagues who have also received this recognition.”