New research from Georgia Tech suggests that a simple change to a chatbot’s instructions could reduce that risk. The work was accepted to the ACM AI Letters publication. 

Researchers Lorenzo de la Loza and Vijay Madisetti tested eight AI models in 1,280 experiments involving simulated conversations about delusional beliefs. They found that instructions designed to discourage excessive agreement reduced the models’ confirmation of those beliefs by 73.8%. Adding a self-reflection step increased the reduction to 77%.

“We think that this paper will help AI providers and solution creators better understand how best to protect and safeguard their users from harming themselves,” Madisetti said. “This may make AI safer for all of us.”

AI chatbots are designed to be helpful and supportive. But that behavior can become risky when a chatbot agrees with a user’s beliefs without questioning whether they reflect reality. Researchers call this behavior sycophancy.

Courtney Crooks, a principal research scientist at the Georgia Tech Research Institute and adjunct faculty member in Georgia Tech’s School of Cybersecurity and Privacy, said chatbot conversations can have both positive and negative effects.

People may feel more comfortable discussing difficult thoughts with a chatbot than with another person. But if the chatbot always agrees, users may miss opportunities to question their beliefs or consider other points of view.

The same behavior that makes a chatbot feel supportive, Crooks explained, can also encourage harmful patterns of thinking.

The researchers tested instructions that told AI models not to reinforce users’ beliefs simply to be agreeable. The team evaluated the models using 16 clinically derived scenarios involving delusional beliefs.

The team also tested other safety tools, including systems designed to flag potentially harmful content. The results suggest that changing a chatbot’s instructions can be an effective way to reduce excessive agreement in the scenarios tested.

Crooks called the findings a promising direction for future research combining psychology and AI safety.

The study did not test people in clinical settings or prove that the approach prevents real-world harm. However, it offers developers a potential way to make chatbots more careful when responding to vulnerable users without building an entirely new AI model.

For more than eight years, MRI, manufacturer of the BoldVu rugged outdoor displays, has supported graduate research in the Microelectronics and Emerging Technologies Thermal Lab (METTL), led by Yogendra Joshi, John M. McKenney and Warren D. Shiver Distinguished Chair in Building Mechanical Systems. The partnership has funded multiple student thesis projects, produced several published papers, and supported engineering improvements incorporated into MRI’s products.

“It’s been a great collaboration,” Joshi said. “Multiple master’s students have completed their thesis projects on different challenges facing the same product line, and they’ve gone on to jobs at premier companies.” 

Ready the full story on the George W. Woodruff School of Mechanical Engineering website

The three-year project, Close-Space Sublimation for Scalable Perovskite Optoelectronics Manufacturing, is led by Liqiu Zheng, assistant professor of physics at Albany State, and Juan-Pablo Correa-Baena, associate professor and Goizueta Junior Faculty Chair in Georgia Tech’s School of Materials Science and Engineering and School of Chemistry and Biochemistry. The researchers aim to develop manufacturing approaches for perovskite thin films that could make production faster, more material-efficient, and easier to scale.

The award also will expand Albany State’s research capabilities and create hands-on learning opportunities for students at both institutions.

Georgia Tech launched the Research Collaboration Forum (RCF) in 2023 to bring together researchers from Georgia Tech and historically Black colleges and universities, as well as representatives from industry, federal agencies, and national laboratories. Participants develop partnerships and pursue new research opportunities.

Through its Seed Grant Program, the forum provides early-stage funding to help teams generate preliminary results, build capacity, and compete for larger external awards. Grants have ranged from $10,000 to $50,000. The Georgia Tech-Albany State team was among the projects funded during the forum’s inaugural cycle.

"The RCF seed funding allowed us to establish the collaboration, generate preliminary data, and demonstrate that our teams could work effectively together," Correa-Baena said. "That initial year helped us identify the key scientific questions and provided the foundation for the new three-year, $1.3 million NSF award."

The project reflects a central goal of the RCF: helping promising collaborations move from initial conversations to sustained research partnerships with national impact.

"By bringing together Georgia Tech researchers, HBCU faculty, industry partners, and federal stakeholders, we are building research capacity, strengthening long-term collaborations, and creating pathways to larger funding opportunities," said George White, director of strategic partnerships at Georgia Tech.

The award will support new thin-film manufacturing and characterization equipment at Albany State. The investment will help researchers accelerate materials discovery, build long-term research capacity, and give students access to advanced semiconductor research tools.

“This award elevates the research footprint of Southwest Georgia and recognizes Albany State’s ability to contribute to nationally relevant scientific research,” Zheng said. “Beyond the research, it creates opportunities for students to gain experience with advanced semiconductor technologies and helps strengthen the pipeline of talent entering the semiconductor workforce.”

Albany State and Georgia Tech will jointly study thin-film growth, structure, and device performance. As part of the collaboration, Georgia Tech researchers will support Albany State as the team acquires and begins using the new equipment, sharing expertise in operation, data collection, and analysis.

Students will receive hands-on training in thin-film deposition, X-ray characterization, solar-cell fabrication, and data analysis. The project also includes exchanges between Georgia Tech and Albany State, giving students access to research facilities, expertise, and collaborative research opportunities at both institutions.

The research focuses on a manufacturing technique known as close-space sublimation. Researchers typically produce perovskite thin films using liquid inks. Close-space sublimation instead uses heat to transport material as vapor across a short distance. The team will investigate whether the approach can be adapted for perovskite materials, potentially enabling faster, more material-efficient, and more scalable manufacturing.

The progression from a Research Collaboration Forum seed grant to a federally funded research project illustrates the forum’s broader goal: helping Georgia Tech and HBCU researchers turn early connections into sustained collaborations that expand opportunity, strengthen research capacity, and advance discovery.

Hosted by Georgia Tech's Strategic Energy Institute (SEI), the annual summit brought together representatives from academia, industry, government, national laboratories, and nonprofits to discuss strengthening energy systems and preparing for a changing energy future. Topics focused on collaboration, workforce development, and strategies for building resilience amid the challenges in the energy sector.

"Energy resilience requires more than technological innovation. It depends on strong partnerships across universities, industry, government, and national laboratories," said SEI Executive Director Yuanzhi Tang, who delivered the summit’s opening remarks. "The UEILC Summit serves as an important forum to exchange ideas, identify shared challenges, and build collaborations among energy institutes across the country. These efforts are essential to strengthening energy systems and preparing the workforce that will support them."

Following Tang, Tim Lieuwen, Georgia Tech's interim president and executive vice president for Research, delivered a keynote address on academia's role in advancing a resilient energy future. Lieuwen emphasized the unique role of universities as trusted conveners and honest brokers, bringing together stakeholders with diverse perspectives to navigate an evolving energy ecosystem. 

A fireside chat featuring Mike Caravaggio of EPRI, Stephanie Gossman of Georgia Power, and Tang explored how artificial intelligence, data center expansion, and rising electricity demand are reshaping the energy landscape. The speakers also discussed how their organizations are working to strengthen grid reliability, expand infrastructure, and support a reliable energy future.

Founded with support from the Alfred P. Sloan Foundation to strengthen collaboration among university energy institutes, the University Energy Institute Leadership Collaborative provides a forum for advancing energy research, education, and engagement.

“A systems approach to today’s energy challenges — where academia, industry, and government collaborate to provide many perspectives on a problem — can only happen if there is a venue and a community where these discussions can safely take place,” says Daniel Tkacik, executive director of Carnegie Mellon’s Scott Institute for Energy Innovation as well as the principal investigator of the Sloan Foundation grant that supports the UEILC. “This summit continues to provide that valuable venue for collaboration, and we are grateful to our generous hosts at Georgia Tech.”

The summit theme, Expanding Collaborations for Resilient Energy Futures, framed discussions on regional energy resilience, grid vulnerabilities, geopolitical influences on energy planning, the growth of data centers, and workforce education. 

"The UEILC annual summit provides an excellent opportunity for energy institute leaders from across the nation to come together and share perspectives, strengthen partnerships, and advance solutions that can help shape more resilient energy futures," said Christine Conwell, director of planning and operations at SEI. "The conversations over the course of the summit reinforced the importance of cross-sector partnerships in creating new opportunities for innovation."

Conversations and networking opportunities provided a broader understanding of how different regions are strengthening energy resilience, addressing emerging threats to power infrastructure, adapting to geopolitical and economic shifts, and preparing for increased electricity demand driven by artificial intelligence and data centers.

"It was exciting to see so many diverse perspectives united by a common goal of building more resilient energy systems," said Jordann Britt, SEI program manager and a UEILC Bridge-Builder Fellow. 

Britt helped organize the summit as part of the UEILC Bridge-Builder Fellows Program, which supports emerging leaders in the university energy community.

The strategy, announced in July 2026 as part of Panama’s National Agenda on Advanced Technologies, was developed through a partnership between Panama’s National Secretariat of Science, Technology, and Innovation (SENACYT) and Tech AI, Georgia Tech’s AI solutions developer. The effort brought together leaders from government, academia, industry, and civil society.

The strategy identifies priorities for AI across economic development, workforce preparation, digital infrastructure, governance, research, and international collaboration.

Pascal Van Hentenryck, the A. Russell Chandler III Chair and professor at Georgia Tech and director of the National Science Foundation (NSF) Artificial Intelligence Institute for Advances in Optimization (NSF AI4OPT), helped lead the development of the strategy.

“Panama has a unique opportunity to leverage its position as a global logistics and financial hub to become a trusted leader in AI,” Van Hentenryck said. “The strategy lays out what is needed to develop the talent, infrastructure, data, and institutions to support that ambition.”

Panama’s focus on artificial intelligence comes as the country expands its role in Latin America’s technology ecosystem. The 2025 Latin American Artificial Intelligence Index classified Panama as an “Adopter” nation and reported a 1.47-point increase in the country’s score from the previous edition.

Building the strategy

Van Hentenryck and Timothy M. Brown, interim managing director of Tech AI at Georgia Tech, authored the strategy following months of engagement with stakeholders throughout Panama.

The process included workshops, interviews, and a nationwide survey that gathered input from more than 6,700 Panamanians. Government officials, researchers, industry representatives, educators, and community members contributed perspectives on the country’s opportunities and challenges.

“The strategy was shaped by what we heard from people across Panama,” Brown said. “That input helped identify where AI can have the greatest impact and what Panama needs to build the capacity to use it effectively.”

The resulting framework is organized around five foundational pillars:

1. Governance and regulatory framework
2. Human talent and institutional capacity
3. Data and infrastructure
4. Ethics, inclusion, and sustainability
5. International cooperation and global standards

Together, the priorities are intended to support AI adoption across sectors including logistics, financial services, healthcare, agriculture, education, manufacturing, government services, and energy.

At the center of the strategy is a vision for Panama to become “Latin America’s Trusted Hub for AI Innovation.” The plan builds on the country’s established role in global logistics and finance, envisioning a “Digital Canal” that supports the secure movement of data, technology, talent, and innovation throughout the region.

Eduardo Ortega-Barría, national secretary of science, technology, and innovation at SENACYT, said the strategy provides a foundation for Panama to participate more fully in the global AI economy.

“AI is transforming economies, societies, and the way we work,” Ortega-Barría said. “For Panama, this strategy is about preparing our country to participate in that transformation while ensuring that innovation creates opportunities for our people and strengthens our competitiveness.”

Connecting research and policy

The strategy reflects contributions from Georgia Tech researchers and experts, SENACYT leadership, policymakers, international advisers, and private-sector stakeholders. AMD also participated in the initiative.

Keith Strier, senior vice president of Global AI Markets at AMD, said international partnerships will be important as Panama develops its technology ecosystem.

“Panama is building its domestic AI capabilities and infrastructure together with the United States as a strategic partner,” Strier said. “This is an important moment as Panama establishes its role in the global AI ecosystem.”

For Georgia Tech, the project illustrates how the Institute’s research and technical expertise can inform national-level technology planning.

Rather than focusing solely on AI development, the strategy connects technical capabilities with workforce preparation, research capacity, infrastructure, entrepreneurship, cybersecurity, and responsible governance. It also calls for efforts to expand access to AI opportunities in rural and underserved communities.

Van Hentenryck said developing the strategy required understanding Panama’s priorities alongside the opportunities presented by emerging technologies.

“Working on a national strategy requires bringing together different perspectives,” he said. “Panama has its own strengths, challenges, and ambitions, and those were essential to shaping a strategy that can work for the country.”

From strategy to implementation

The launch marks the beginning of the next phase: putting the strategy into action.

The road map includes recommendations for expanding AI education and workforce training, strengthening research capacity, improving digital infrastructure and cybersecurity, establishing responsible AI governance, and creating mechanisms to support entrepreneurship and innovation.

Franklin Morales, head of the International Technical Cooperation Office at SENACYT and project lead for the AI initiative, said the strategy provides a starting point for that work.

“Now this is not the end. It is not even the beginning of the end. But it is, perhaps, the end of the beginning,” Morales said, quoting Winston Churchill. “After months of work, Panama launched its National Artificial Intelligence Strategy, a vision of what this country needs to build for a new technological era.”

“The launch of the strategy is an important milestone, but the real work begins with implementation,” Brown said. “The focus now is on turning these priorities into lasting capacity, developing talent, and infrastructure while supporting research, entrepreneurship, and responsible AI adoption.”

For Panama, the strategy establishes a framework for using artificial intelligence to strengthen economic competitiveness, expand opportunity, and support the country’s role in an increasingly technology-driven global economy.

NSF has awarded $20 million to renew the National AI Institute for Advances in Optimization (NSF AI4OPT) through 2031 and $18.4 million to renew the National AI Institute for Adult Learning and Online Education (NSF AI-ALOE) for a new five-year period. The awards will support research at the intersection of artificial intelligence and optimization, as well as the development of AI technologies for adult learning, higher education, and workforce development. A third Georgia Tech-led National AI Institute, the AI Institute for Collaborative Assistance and Responsive Interaction for Networked Groups (AI-CARING), will continue its research under a one-year no-cost extension.

Together, the institutes represent a broad range of AI research at Georgia Tech, with work spanning energy systems, advanced manufacturing, education, reskilling, and workforce development.

The renewed investments come as NSF continues to prioritize artificial intelligence, advanced research infrastructure, and development of the nation’s STEM workforce.

“Georgia Tech has built a nationally recognized ecosystem for artificial intelligence research, education, and application,” said Tim Lieuwen, interim president and executive vice president for Research at Georgia Tech. “These NSF investments recognize the strength of our researchers and the importance of advancing AI in ways that address real-world challenges. The continued support for NSF AI4OPT and NSF AI-ALOE will allow Georgia Tech researchers to push the boundaries of what AI can accomplish while preparing students, educators, and the workforce for an increasingly AI-enabled future.”

Advancing AI-Powered Decision-Making

The $20 million renewal of NSF AI4OPT builds on five years of research at the intersection of artificial intelligence and mathematical optimization.

Led by Pascal Van Hentenryck, the A. Russell Chandler III Chair and professor in the H. Milton Stewart School of Industrial and Systems Engineering at Georgia Tech, NSF AI4OPT develops AI and optimization technologies for complex systems where decisions must be made quickly, efficiently, and under uncertainty.

In its next phase, the institute will place greater emphasis on real-time and interactive optimization, advancing scalable, efficient, and trustworthy approaches to decision-making. Research will continue to address challenges in areas such as energy, supply chains, transportation, and advanced manufacturing.

“NSF AI4OPT’s first five years demonstrated the power of bringing AI and optimization together to address some of the most challenging decision-making problems facing society,” said Van Hentenryck. “This renewal gives us the opportunity to build on that foundation and develop AI systems that can reason, optimize, and make decisions in real time. We are especially excited about advancing trustworthy AI for complex systems in energy, supply chains, and manufacturing, while continuing to educate the next generation of AI researchers and practitioners, starting with middle and high schoolers.”

NSF AI4OPT combines artificial intelligence, mathematical optimization, and computing to create systems that support decisions in complex and dynamic environments. Its research includes applications in critical infrastructure and industry, where decisions often involve competing objectives, uncertainty, and rapidly changing conditions.

The institute also has an education and workforce development mission, introducing AI and optimization concepts to students and educators while preparing learners for an AI-enabled workforce.

“NSF AI4OPT represents exactly the kind of interdisciplinary research that Georgia Tech is positioned to lead,” said Raheem Beyah, provost and executive vice president of Academic Affairs at Georgia Tech and former dean of the College of Engineering and Southern Company Chair. “The institute connects foundational advances in artificial intelligence and optimization with engineering challenges that have direct implications for our economy and society. Its continued investment in research and education strengthens Georgia Tech’s ability to prepare students to lead in a rapidly changing technological landscape.”

Advancing Adaptive Expertise Through AI

NSF AI-ALOE’s renewed $18.4 million award launches the institute’s next five years of research into how artificial intelligence can transform adult learning and online education.

The renewal builds on NSF AI-ALOE’s previous work, including the development of seven AI agents and a data architecture for AI-augmented learning. Its next phase will focus on adaptive expertise, or the ability to apply and transfer learned skills to new situations.

AI-ALOE’s research in Phase 2 will expand beyond traditional educational settings into workplace and vocational training, with a focus on occupational skills in areas including advanced manufacturing and data science.

NSF AI-ALOE will also build on advances in generative and agentic AI to develop AI agents that support the acquisition of complex skills across higher education and workplace environments.

“NSF AI-ALOE’s renewal reflects an important shift in how we think about AI and learning,” said Ashok Goel, director of NSF AI-ALOE and professor of computer science and human-centered computing in the School of Interactive Computing at Georgia Tech. “Our goal is not simply to use AI to deliver more content or automate instruction. We are exploring how AI can help people develop adaptive expertise, so they can transfer what they learn to new and changing situations. That has enormous implications for higher education, workforce development, and lifelong learning.”

The institute’s research will examine four dimensions of AI-supported learning: scalability, personalization, transfer of learned skills, and whole-person learning. It will also advance foundational AI research in machine teaching, metacognition in AI agents, and mutual theory of mind between humans and AI agents.

NSF AI-ALOE will use the data architecture developed in Phase 1 that is capable of ingesting, standardizing, analyzing, and visualizing information generated through interactions with AI tools, learning management systems, and student information systems. Researchers will use that data to better understand how learners and instructors interact with AI and improve AI-powered learning technologies.

The institute is also expanding partnerships with higher education institutions and industry. Its research network includes five colleges and universities and six industry partners in advanced manufacturing and related fields, creating opportunities to reach as many as 370,000 learners nationally through skilling, reskilling, and upskilling efforts.

“AI is changing both what people need to learn and how they can learn it,” said David Joyner, Zvi Galil PEACE Chair in the College of Computing and interim vice provost for AI in Education at Georgia Tech. “NSF AI-ALOE is uniquely positioned to study that transformation at scale. Its work can help us understand how AI can support learners without replacing the human elements of education, while giving people new ways to build and apply skills throughout their lives and careers.”

Continuing AI-CARING’s Research

The renewed support for NSF AI4OPT and NSF AI-ALOE builds on Georgia Tech’s broader participation in the National AI Institutes program.

Georgia Tech’s AI-CARING Institute will continue its research under a one-year no-cost extension, allowing the institute to carry forward its research objectives and partnerships.

The continued work of AI-CARING, alongside the renewed investments in NSF AI4OPT and NSF AI-ALOE, reflects the breadth of Georgia Tech’s AI research community and its work across disciplines.

From AI Research to Real-World Impact

The renewed NSF investments build on Georgia Tech’s broader efforts to advance AI research, education, and application through Georgia Tech AI and Tech AI.

Georgia Tech AI connects Tech’s AI community across research, education, and impact. Tech AI complements this work by serving as Georgia Tech’s engineering and delivery arm, bringing together researchers, engineers, research software engineers, students, and technical expertise to move AI projects from early-stage concepts toward operational systems.

This connection helps create a pathway from foundational research to technologies that can be developed, tested, and deployed in real-world settings.

For NSF AI4OPT, that work includes AI systems that support complex decisions in critical systems and industries, from energy and manufacturing to supply chains and transportation. For NSF AI-ALOE, it includes AI technologies that help people acquire, apply, and transfer skills across classrooms, workplaces, and lifelong learning environments.

Tech AI works at the application and deployment stage, partnering with researchers, industry, and public-sector organizations to develop and implement scalable AI solutions. Its work spans AI engineering and solution delivery, applied research, industry and government partnerships, workforce development, and responsible and trustworthy AI.

“Georgia Tech’s strength in AI comes from the connections between research, talent, and application,” said Timothy M. Brown, managing director of Tech AI. “Our NSF AI Institutes advance research across critical areas, while Tech AI serves as Georgia Tech’s engineering and delivery arm, working with industry and public-sector partners to turn AI expertise and research into deployable solutions. Together, these efforts create a pathway from AI innovation to real-world impact.”

Together with AI-CARING and Georgia Tech’s broader AI research community, the institutes contribute to a universitywide effort to advance AI that is technically innovative, human-centered, and designed for meaningful impact.

“AI is transforming virtually every sector, and Georgia Tech has a responsibility to help shape that transformation,” Lieuwen said. “These institutes bring together some of Tech’s strongest capabilities in research, education, and interdisciplinary collaboration. Their renewed support gives us an opportunity not only to advance the science of AI, but also to ensure that the benefits of these technologies reach the people, organizations, and communities that will rely on them.”

About the Georgia Institute of Technology

The Georgia Institute of Technology, or Georgia Tech, is one of the top public research universities in the U.S., developing leaders who advance technology and improve the human condition.

The Institute offers business, computing, design, engineering, liberal arts, and sciences degrees, as well as professional development and K-12 programs for fostering success at every stage of life. Its more than 56,000 undergraduate and graduate students represent 54 U.S. states and territories and more than 146 countries. They study at the main campus in Atlanta, at instructional sites around the world, and through distance and online learning.

As a leading technological university, Georgia Tech is an engine of economic development for Georgia, the Southeast and the nation, conducting more than $1 billion in research annually for government, industry and society.

About the National Science Foundation

The U.S. National Science Foundation (NSF) is an independent federal agency that supports science and technology in all 50 states, the District of Columbia, and U.S. territories. For more than 75 years, NSF has advanced the frontiers of STEM research and innovation. To keep the United States at the leading edge of discovery, NSF funds basic and solutions-oriented research that generates new knowledge to fuel industries of the future, create world-leading technologies, and improve the lives of the American people.

After a grueling, world-class competition, the team won the $4 million first-place prize in August 2025. 

The team has since disbanded. Some members have moved into the corporate world, while others continue in academia. Despite these varied paths, Team Atlanta’s search for breakthrough AI cybersecurity solutions continues.

From AIxCC to Microsoft

Team Atlanta lead Taesoo Kim, principal security researcher Dongkwan Kim, and three other former team members joined Microsoft Security after the competition, where they continue to work on AI and cybersecurity in the Frontier Offensive Research & Generative Exploitation (FORGE) Lab.

The move has given the researchers an opportunity to apply concepts from AIxCC to real-world software. It has also exposed them to challenges that are difficult to replicate in a competition or research lab.

Dongkwan Kim said that team members continue to share what they learned through research papers, reports, software, and benchmarks. At Microsoft, these lessons are tested against real customer code.

This work led to MDASH, Microsoft's multi-agent, multi-model system for vulnerability discovery and remediation. The system uses more than 100 AI agents to search for vulnerabilities, validate potential findings, and help develop fixes.

Rather than asking a single AI model if a piece of code contains a vulnerability, MDASH can examine a problem using multiple agents. The system can also try to create an exploit to determine whether a potential vulnerability is real and reachable.

For Dongkwan Kim and the other former Team Atlanta members at Microsoft, moving from AIxCC to MDASH showed how research can look different when applied to real software.

“AIxCC was not an endpoint for Team Atlanta,” he said. “We continue sharing what we learned through technical reports, papers, open artifacts, and benchmarks for vulnerability discovery and patching.”

Working with customer code introduced new challenges for the Microsoft team. The researchers had to consider security boundaries, existing development processes, how findings would be reviewed, and how vulnerabilities would be prioritized for action.

These challenges created a new feedback loop between research and product development. The team took ideas from AIxCC, test them on real software, learn where they worked and where they fell short, and use those lessons to improve the system.

The experience also showed that AI does not replace the need for cybersecurity experts. Human researchers are still needed to provide context, decide how to break down difficult problems, validate findings, understand attack paths, and determine the potential impact of a vulnerability.

Taesoo Kim, a professor in the School of Cybersecurity and Privacy and vice president of security research at Microsoft, said the competition continues to influence the Microsoft team's work.

“Every single activity that we’ve done at Microsoft was influenced by AIxCC,” he said in a 2026 interview with Microsoft.

The work has continued to grow. In 2026, Microsoft introduced MAI-Cyber-1-Flash, an AI model built specifically for cybersecurity and designed to work with MDASH.

The model is designed to handle many of MDASH's tasks while allowing larger AI models to focus on harder problems. Microsoft reported that replacing 80% of the models used by MDASH with MAI-Cyber-1-Flash increased its performance on the CyberGym benchmark from 88.4% to 95.95%.

The benchmark includes more than 1,500 examples from 188 software projects. Microsoft also reported that the new setup can achieve similar performance at half the cost of the previous MDASH configuration.

“AIxCC has sparked cybersecurity innovation across the globe, from frontier AI companies to small academic labs,” said Taesoo Kim. “It is an incredibly exciting time to be working in AI-driven security engineering and research, as we see AI fundamentally reshape how we find and fix vulnerabilities at scale.”

Continuing the Research at Georgia Tech

The AIxCC experience also continues to shape cybersecurity research at Georgia Tech.

Jiho Kim, a Georgia Tech Ph.D. student who was part of Team Atlanta's research efforts, said one of the biggest lessons he’s brought back to campus was learning how AI and traditional security tools can work together.

One of these tools is fuzzing. Fuzzing tests software with large numbers of inputs to detect unexpected behavior or security problems. Large language models (LLMs), meanwhile, can reason about code and help guide the search.

During the AIxCC competition, the Team Atlanta combined these ideas in CtxFuzz, a system that uses an LLM to help guide fuzzing toward parts of software that may contain vulnerabilities.

The research was submitted to the ACM/IEEE International Conference on Automated Software Engineering, where it received the ACM Distinguished Paper Award.

“Since AIxCC, we’ve continued building on some of the core findings from our two-year journey with Team Atlanta,” Jiho Kim said.

“One of the biggest lessons for us was understanding how LLMs and traditional fuzzing can work together in a mutually beneficial way, using each to overcome the limitations of the other and ultimately find more and deeper vulnerabilities.”

The researchers also wanted to make the lessons from AIxCC useful to other cybersecurity researchers.

They created an Open-Source Cyber Reasoning System Framework (OSS-CRS) and CRSBench, which provides researchers and security professionals with ways to use, test, and build on technology developed through AIxCC.

“We’ve also been focused on making the results of AIxCC useful to the broader security community,” Kim said. “We created OSS-CRS and CRSBench so that researchers and practitioners can more easily use, reproduce, and build upon the capabilities and lessons from our AIxCC work.”

The team's research has also moved beyond identifying vulnerabilities. Researchers are studying how well AI models can understand and reason about computer code.

Jiho Kim and his lab mates in the Systems Software & Security Lab developed COIN, a benchmark designed to test how well LLMs can reason about code. The work has been accepted to the 2026 Conference on Empirical Methods in Natural Language Processing.

The Georgia Tech researchers are also developing additional benchmarks to study the various types of reasoning required for cybersecurity. They are using what they learn to create new datasets and methods for training AI models focused on cybersecurity.

“We’re using what we learn from these benchmarks to train cybersecurity-focused models through new datasets and training methodologies,” Jiho Kim said.

Photos by John Popham/College of Computing

Cognitive behavioral therapies require patients to practice skills between sessions. Clinicians rely on retrospective patient reports to understand what happens during that time.

However, recall bias, selective disclosure, and difficulty remembering can render those reports subjective, incomplete, or inaccurate.

Clinicians can now see sensor data on how patients’ bodies react in these situations thanks to a new technology toolkit from Georgia Tech and Emory University.

A new app that syncs with a FitBit wearable device can track and record heart rate, step count, noise level, and other sensor data when patients practice prolonged exposure homework assigned by their therapists.

A web dashboard lets clinicians review that data, add notes, and track patient progress. This information helps them structure therapy sessions more effectively and accelerate patient progress.

The toolkit is the culmination of a $1.2 million National Science Foundation grant awarded to Georgia Tech’s Rosa Arriaga and Emory’s Andrew Sherrill in 2019.

Arriaga is an associate professor at Tech’s School of Interactive Computing. Sherrill is an assistant professor in the Department of Psychiatry and Behavioral Sciences at the Emory School of Medicine.

Sherrill is also a practicing clinical psychologist at the Emory Healthcare Veterans Program and has worked with veterans with PTSD for more than a decade. 

Arriaga and the students in her Ubicomp Health and Wellness Lab spent five years developing the toolkit, which they call the Patient Engagement Computational Sensing System (PECSS).

“It was a lot of master’s students and undergrads who built the back end to the app and the dashboard,” Arriaga said. “It was a lot of work and effort by a lot of students to take an idea from conception to deployment.”

The researchers originally titled the toolkit the Prolonged Exposure Collecting Sensing System, but they changed the name after realizing it could be used for other types of therapy.

“The idea is that for any therapy that has a homework component, this can bridge the gap between patient self-reporting and clinician intuition,” Arriaga said.

Nathaniel Swinger, a Ph.D. student in Arriaga’s lab, co-led a paper on the study’s results along with Ph.D. student Myeonghan Ryu. Their paper received a best paper award at the 2026 ACM Conference on Computer-Supported Cooperative Work and Social Computing (CSCW). Best papers are given to less than 1% of the papers published at the conference.

“Our findings showed that the deployment was quite successful,” Swinger said. “Over 75% of the patients who incorporated PECSS into their treatment experienced a clinically significant change in symptoms. We don’t know if that’s causal, but there is some evidence the system worked to facilitate the process.”

Prolonged exposure is a method for systematically approaching trauma memories and reminders to make them safe and tolerable for patients. It is typically delivered in one-on-one therapy sessions.

Sherrill said the toolkit shows promise toward enhancing prolonged exposure therapy outside of clinical settings.

“Prolonged exposure has been researched more than any other therapy that exists,” Sherrill said. “We know it’s effective, but we’ve had problems for decades implementing it in the real world.

“There’s a need for technology in taking what patients learn in their sessions and having them replicate it outside of the clinic.”

Until now, the impact prolonged exposure on a patient with PTSD depends on the patient’s willingness to self-report the results of their homework.

“The number of potential triggers is an endless list,” Sherrill said. “We want people to approach them with their guard down and not to engage in avoidance or soothing behaviors.”

Sherrill said most of his patients have shown interest in continuing to use the toolkit — even after therapy is no longer needed.

“A system like this could reduce the frequency of sessions with a therapist,” Sherrill said. “We’re teaching patients to be their own therapists. This toolkit gives them a greater sense of independence.”

Given the promising results, Swinger said that ideally the next step would be a large-scale clinical trial.

“We’re looking to better test the causal clinical impacts of the system and a more generalizable notion of efficacy,” Swinger said. “We want to rigorously test it in a clinical setting for people beyond veterans with PTSD.”

Researchers at Georgia Tech's Center for Advanced Communications Policy will use the funding to help older adults access assistive technologies that support independent living.

Principal research scientist Nathan Moon and a team of colleagues at the Center for Advanced Communications Policy (CACP) in Georgia Tech’s Ivan Allen College of Liberal Arts were awarded a three-year, $1.5 million grant from the National Institute on Disability, Independent Living, and Rehabilitation Research. The project is in collaboration with the Center for Inclusive Design and Innovation (CIDI) in the College of Design.

The funding will support the ACCESS for Aging Well with Assistive Technology (AT) 2.0 project, which builds on the researchers’ previous work to help older adults live independently.

“As Americans continue to age and we're growing older as a society, we want to ensure that people can continue to live independently and participate in the communities of their choice,” Moon said. “The tools that we have developed here are intended to do that.”
 

In a study accepted for the 2026 ACM Conference on Computer and Communications Security, Georgia Tech researchers interviewed 20 military sailors about their cybersecurity experiences, training, and responses to hypothetical scenarios. Their findings point to a gap between how mariners are trained to handle emergencies and how cyberattacks can compromise the systems they depend on. 

The study found several gaps in how crews prepare for cyber threats:

• Training often misses the mark. Thirteen participants said that standard cybersecurity training was largely irrelevant to their shipboard duties, and 14 reported receiving no mission-specific cybersecurity training.
• Operational technology is often overlooked. Eighteen participants said their training did not distinguish between traditional information technology and operational technology, such as navigation and propulsion systems.
• Obvious failures are easier to recognize. Eighteen participants said they would primarily look for visible signs of operational problems when identifying a potential cyberattack.
• Cybersecurity is often a low priority. Seventeen participants described their cybersecurity training as absent, low quality, or a low priority.

These gaps matter because cyberattacks can compromise a system without causing it to stop working. For example, an attacker could manipulate navigation data, leaving a crew to make decisions based on false information.

“I’d assume it was anything but cyber at first. It would probably take me quite some time to get to that conclusion,” one participant told the researchers.

The team examined three hypothetical scenarios: GPS spoofing, loss of propulsion control in a high-traffic area, and failure of electronic navigation systems in a congested channel at night.

In each scenario, mariners would first focus on keeping the vessel safe, using established procedures to stabilize the ship and troubleshoot its systems. While this response is essential during an emergency, it could delay recognition of an attack if crews do not consider that the system or its data may have been compromised.

For example, a ship navigating a narrow channel depends on accurate location information, but what happens when its navigation systems appear to work normally while a hacker manipulates that data?

An attacker could use GPS spoofing to falsify a vessel’s reported position. If the false position is close enough to the ship’s actual location, a mariner might not notice anything wrong. The vessel could gradually head toward shallow water or another obstacle without triggering an obvious error or alarm.

“By the time the mariner realizes something is wrong, the ship’s size and limited maneuverability could make it too late to avoid a grounding or collision,” said Anna Raymaker, a Georgia Tech Ph.D. student who studies maritime security.

The scenario illustrates a central challenge in maritime cybersecurity: An equipment failure may be easy to recognize, but a cyberattack that provides false information can be much harder to detect.

Batten the Hatches: Cybersecurity with Military Mariners was written by master’s student Ryan Von Brock, Raymaker, Research Scientist Animesh Chhotaray, Associate Professors Frank Li and Saman Zonouz, and Provost & Executive Vice President for Academic Affairs Raheem Beyah.

The research was conducted in Georgia Tech’s Cyber-Physical Security Lab, a collaboration between the School of Cybersecurity and Privacy and the School of Electrical and Computer Engineering. 

Photos by Terence Rushin/College of Computing

Policymakers, health system executives, community leaders and others working to address this challenge now have help from Rural Evaluation and Analytics for Community Health (REACH GA), an advanced decision-support platform that offers a comprehensive view of healthcare use in rural Georgia. In addition to updated information on rural health issues, the platform provides computer-based tools to guide allocation of healthcare resources and explore the potential impact of changes to rural health services. 

“The REACH GA platform provides up-to-date, actionable information to help leaders understand the big picture of healthcare in rural Georgia,” said Jon Duke, M.D., a principal research scientist in the Georgia Tech Research Institute (GTRI) and the project’s principal investigator. “Beyond more accurate data, the platform uses artificial intelligence (AI) and other computer-driven tools to support improved decision-making.”

Of Georgia’s 159 counties, 126 are considered rural. Approximately 24 percent of the state’s 11.3 million residents live in these rural areas.

Read the full article on the GTRI news page

Clark Atlanta University (CAU) is strengthening its artificial intelligence programs through AIHUB@CAU, an initiative supported by a $2.79 million National Science Foundation (NSF) grant and developed in collaboration with Georgia Tech’s NSF AI Institute for Advances in Optimization (AI4OPT). 

One moment they're playing games or watching television. The next, they experience breathing failure, shock, or neurological decline. If the warning signs aren't recognized early enough, the child may require emergency transfer to the intensive care unit (ICU), where interventions can include breathing tubes, blood pressure medications, and other lifesaving measures.

The phenomenon is called “emergent deterioration.” 

"Kids will look fine, and then all of a sudden they'll fall off a cliff and rapidly deteriorate," said Dr. Mark Mai, a pediatric intensivist at Children’s Healthcare of Atlanta, who cares for critically ill children in the ICU. "When those kids go to the ICU and need emergency interventions, they have a much higher rate of death than kids we bring up to the ICU in a controlled fashion."

To help clinicians identify those high-risk patients sooner, researchers at Georgia Tech are partnering with Children's clinicians and technology teams to create an artificial intelligence-powered warning system. Known as Algorithm for Counteracting the Clinical Onset of Rapid Deterioration (ACCORD), the three-year project is one of the first funded projects focused on a software solution by the Children’s Healthcare of Atlanta Pediatric Technology Center at Georgia Tech (PTC). Project teams are working simultaneously on model development, app design, and user testing. And, unlike many healthcare AI projects that remain confined to research papers, ACCORD is being designed from the beginning for use in a real hospital. The ultimate goal is to help clinicians intervene before a child reaches a life-threatening emergency. 

Teaching AI to Spot Trouble Earlier

Today, clinicians rely on an early warning score that combines measurements such as heart rate, blood pressure, and breathing rate into a single risk assessment. While helpful, the approach simplifies a complex clinical picture.

"The current system is a pretty basic rubric that sums up all the data points and then decides whether they are high-risk or low-risk, but from the data science and machine learning perspective it's not optimal," said Kai Wang, an assistant professor in the School of Computational Science and Engineering and project co-principal investigator with Mai.

Rather than evaluating patients through a fixed scoring system, ACCORD's AI model analyzes dozens of data streams, including vital signs, laboratory results, and clinical observations. The goal is to uncover subtle patterns that may signal deterioration hours before the physical warning signs become obvious to clinicians. 

"We want to build a more sophisticated algorithm that can look into vitals, blood pressure, heart rate, and other measures to provide a more granular forecast of risk," Wang said.

Building that capability into an algorithm requires making sense of one of healthcare's biggest challenges: messy, incomplete, and constantly changing data. To develop the model, researchers are training and testing it using information pulled from Children's electronic health records. Some information, such as vital signs, is collected continuously. Other information may be recorded less frequently or at irregular intervals, such as nursing observations.

"That is both the most challenging and the most exciting part of this project," said Himadri Pandey, a Ph.D. student in H. Milton Stewart School of Industrial and Systems Engineering working on ACCORD. "We have to consider the realities of a healthcare setting. Data may be incomplete or delayed, staffing and resources may change, and any recommendation must be understandable and usable by clinicians."

"The goal is not simply to build a model that works mathematically," she added. "It's to build something that could genuinely support decision-making in a hospital."

Building Technology Nurses Will Use

For ACCORD to improve patient outcomes, the technology must fit naturally into clinicians' daily workflow. Most nurses care for multiple patients simultaneously and cannot continuously monitor a single child. Because episodes of emergent deterioration are relatively rare in a full day of care, opportunities to gain experience recognizing the earliest warning signs can be limited. Acknowledging that reality, project leaders involved frontline nurses from the beginning.

"We went straight to the nurses and said, 'This is what we're trying to do. You tell us what would make your job easier, how you need the flow, what it needs to look like, and we will build according to that,” said Christina Roberts, program manager for PTC and the Health Informatics Core at Children’s. "We brought them into the process very early and gave them a say in the development, so they know exactly what to expect when the tool comes to the floor."

The team plans to integrate ACCORD directly into the Children’s electronic health record system, where clinicians already access patient information. The application will combine vital signs, laboratory results, and other clinical data into a single dashboard that can automatically flag patients at elevated risk of deterioration.

Researchers and clinicians continue to meet regularly as the platform evolves.

"How do we distinguish what the algorithm finds important and what is just always there?" said Dr. Claire Stokes, a pediatric hematologist and oncologist with the Aflac Cancer and Blood Disorders Center at Children’s, who is involved in the project. "Because a clinician probably always wants to see the vital signs, even if they're not alert levels, for example."

Those conversations help ensure that the system provides useful information without overwhelming clinicians with additional data or alerts. The team hopes to begin testing the system in clinical settings by 2027 before broader deployment. For the researchers working on ACCORD, however, the project's success will ultimately be measured by the patients it helps.

"I know that one research project cannot solve every problem in healthcare," said Pandey, who has experienced the hospitalization of a close family member. "But being able to contribute, even in a small way, allows me to replace some of that earlier helplessness with purpose."

If successful, ACCORD could give clinicians something they rarely have when a child begins to decline — time. 

As AI systems become more agile with expanded access to tools, computer networks, and other real-world systems, finding better ways of identifying and preventing risky AI behavior becomes even more urgent. Still, high-profile incidents of AI behaving in unintended or dangerous ways are rare, which makes them difficult to study and understand. 

“If we can understand and detect what changes inside an AI model right before it begins behaving in unsafe or misaligned ways, we may be able to inform more effective safeguards,” said Eyas Ayesh, a second-year Ph.D. student in Georgia Tech’s School of Psychology and graduate fellow at the Center for Computation and Cognition.

Ayesh and his advisor, Assistant Professor Anna Ivanova, are developing a probe designed to identify internal activity patterns associated with harmful behaviors in large language models. Their work is supported by a $300,000 award from Coefficient Giving.

Misbehaving Models

Training a probe requires examples of both desirable and undesirable behavior researchers can teach it to distinguish between them. Because deceptive or unsafe responses can be rare and highly dependent on the model, prompt, and context, researchers may not have enough examples to determine what causes the behavior or how to recognize it the next time.

But an unexpected finding in AI research gave Ayesh an idea. In studies of a phenomenon known as emergent misalignment, researchers found that fine-tuning models on a narrow harmful task could lead them to produce a much wider range of problematic responses to unrelated prompts. For example, researchers found that fine-tuning a model to write insecure code without warning users could lead to other concerning behaviors unrelated to coding.

Ayesh realized he could use that phenomenon to solve the problem of scarce data. Starting with open-source AI models, Ayesh fine-tuned them to display targeted undesirable behaviors more frequently. Then, he analyzed different versions of the deliberately misaligned models using a probe that monitors the internal activity of the model.

The probe works somewhat like a pattern detector, looking at activity inside the model as it generates responses and searching for patterns associated with particular behaviors. Researchers can then train a classifier to distinguish patterns associated with desirable behavior from those associated with harmful behavior.

“Just as different parts of the brain turn on and off when people do different tasks, so do the different parts of an AI model,” Ayesh said. “When a model produces a specific type of response — such as deceptive statements or harmful advice — we may observe recurring patterns in its internal activity. We refer to these patterns as representations of a behavior.”

Inside the Black Box

Ayesh is now testing whether the internal patterns he identified remain consistent across differently tuned AI models. Early results suggest that signals identified in deliberately misbehaving models can also be detected in their original versions.

The next step is determining whether those signals can help researchers identify or flag concerning behavior in models that have not been deliberately fine-tuned to misbehave. 

“I hope our research in AI safety can help develop some guardrails and some ways to both identify and prevent misaligned behavior in AI systems, given how much of an impact they're already having on the world,” he said. 

Ayesh is a member of Georgia Tech’s AI Safety Initiative, which brings together researchers across disciplines to study and improve the safety of increasingly capable AI systems.

Ivanova said the value of their research lies partly in approaching AI safety from a fundamental science perspective.

“As scientists, we have been trained to think about the underlying mechanisms and causes of the behaviors we observe,” Ivanova said. “For us, it's important to develop a fundamental understanding of how these models work, or we will risk missing the bigger picture.”

However, a new paper by a Georgia Tech-led research team suggests that the requirements can disproportionately burden family farms and other small food producers due to a lack of technological infrastructure, resources, or compliance expertise.

The rule is mandated by Section 204(d) of the Food Safety Modernization Act, which Congress passed and President Barack Obama signed into law in 2011. Intended to help the FDA quickly identify the source of contamination, the rule requires producers or distributors with more than $25,000 in annual produce sales to comply or face significant fines. 

Earlier this year, the FDA extended its compliance deadline to July 2028. One reason for the extension may be the volume of feedback from stakeholders affected by the rule. The FDA received more than 1,200 comments during an open forum, with feedback from stakeholders ranging from major distributors to small farmers. 

“Many small farmers commented on how they may not have the devices needed to input this data,” said Soonho Kwon, a Ph.D. student in Georgia Tech’s School of Interactive Computing (SIC) and lead author of the paper. “Does this mean they have to purchase it themselves? Do they need to become educated on how to use computing systems?”

Kwon is a member of the Equity and Sustainability in Computing Lab, which is led by SIC professor and chair Shaowen Bardzell.

Many small farms also said they can’t afford to hire someone to track the data.

One small farmer said the amount of data tracking required by the rule is overwhelming. Some of the required data include:

• location and name of the field where food was harvested
• date of harvest
• packing dates
• shipping dates

“Please do not force us to do technology stuff,” the commenter said. “It’s hard enough to keep up with the local demand as it is. We run a pretty low digital technology effort. It’s basically harvest fresh organically grown veggies and sell them to local people.”

Kwon said the intention of the Food Traceability Rule is admirable.

“Preventing foodborne illness is critical, and data- and technology-driven governance can be a powerful tool toward that goal,” he said. “But it’s equally important to think critically about who is supposed to be the default user of these systems, and who gets missed in the process. It’s undermining the people who are unable to comply.”

Other factors didn’t appear to be considered by the FDA, including the lack of technological infrastructure in rural America, where many foods are grown.

“Many parts of rural America have limited or unreliable internet access,” Kwon said. “If the FDA wants them to send this data, they must comply within 24 hours. Does that mean they have to stop their daily routine and drive to a city that has internet to send it? The rule is operating on the assumption that everyone is dealing with the same physical environment.”

Culture and religion also seem overlooked. Some commenters raised concerns that Amish farmers who avoid certain technologies for religious reasons would be pressured into digital record keeping.

Many major distributors and organizations expressed support for the Food Traceability Rule in the FDA’s forum. Catherine Wieczorek, a Ph.D. student in SIC and co-author on the paper, said these organizations don’t have the same tension points as smaller producers.

“Larger food producers have the operational capacity to do the type of work the rule requires,” Wieczorek said. “We find there’s a power imbalance when it comes to smaller food producers like a family farm. Change at that scale is difficult for smaller producers.”

Bardzell, who advises Kwon and Wieczorek, said the situation provides computing researchers an opportunity to create interventions that will benefit those with fewer resources.

“In a data age when we’re adding AI into our work processes and labor practices, we need to think about how this need creates unequal burdens on different stakeholders in our food system,” Bardzell said. “It’s a significant challenge for computing going forward.”

Kwon will present the paper on behalf of his collaborators next week at the ACM Conference on Computer-Supported Cooperative Work and Social Computing (CSCW) in Salt Lake City, Utah. Their research is supported by the National Science Foundation.

Georgia Tech researchers have developed a tool that can recover deleted conversations from AI assistants running on Android phones. The tool, called ORISA, can also rebuild the recovered information into a working AI session.

The findings show that deleting an AI conversation on a phone does not necessarily mean it removes every trace.

The research could give digital investigators a new way to recover information from phones. It also raises privacy concerns for people who use AI assistants that run locally on their devices.

Local AI assistants run directly on a phone rather than sending conversations to a cloud service. While the local assistant is running, information from conversations can remain in the phone’s working memory even after it is deleted.

ORISA searches this memory for pieces of deleted conversations.

In one experiment, researchers created a fictional AI assistant called “Project Note Keeper” using the ChatterUI Android app. They gave it 100 fictional facts about a project, then deleted the conversation.

ORISA recovered information from the deleted conversation and used it to create a new working session. When researchers asked the restored assistant to list the project notes it had been given, it returned 26 facts. The original session could access only 14 facts because the rest had fallen outside its active memory.

The experiment showed that researchers could recover information the AI had already stopped actively using.

“It can help establish what information someone shared with an AI assistant and what assistance they received,” said Ph.D. student Ken Xu, lead author of the study.

The researchers tested ORISA with 10 Android apps and three AI models. Across 60 test configurations, the tool recovered conversation information that remained in the phone’s memory.

The researchers say the information becomes harder to recover as the phone’s memory is overwritten by other activity.

The research was presented at the 2026 IEEE Symposium on Security and Privacy. The paper, titled Recovering and Rehosting Mobile Local LLM Conversations and Contexts via Memory Forensics, was authored by Ph.D. students Xu, David Oygenblik, Runze Zhang, and Mingxuan Yao; Research Scientist Muhammad Ibrahim; and Associate Professor Brendan Saltaformaggio. The work was done in Georgia Tech's Cyber Forensics Innovation Laboratory, a collaboration between the School of Cybersecurity and Privacy and the School of Electrical and Computer Engineering. 

ATLANTA — Georgia Tech has received an initial $2.25M for the first year of the program, marking the beginning of a $5 million overall commitment from Google.org to help more scientists across the country use artificial intelligence (AI) to advance their research. 

ATLANTA — Georgia Tech has received an initial $2.25M for the first year of the program, marking the beginning of a $5 million overall commitment from Google.org to help more scientists across the country use artificial intelligence (AI) to advance their research. 

Students will work with faculty mentors from both institutions and complete advanced coursework and a capstone project focused on developing and applying technologies in healthcare. The master’s degree is offered through Georgia Tech’s interdisciplinary Master of Science in Robotics program, which brings together faculty and expertise from six schools, including the Wallace H. Coulter Department of Biomedical Engineering.

According to Jaydev Desai, professor and Cardiovascular Biomedical Engineering Distinguished Chair in the Wallace H. Coulter Department of Biomedical Engineering, the pathway will help future physicians develop the technical expertise to understand and apply emerging technologies as they shape patient care.

Read the full story on the Emory School of Medicine website.

AI agents don’t go rogue. That’s something only humans do.

Nevertheless, a New York Times article – representative of much news coverage of AI – described an OpenAI hacking as “A.I. bots going rogue and independently spearheading a cyberattack.”

Name-brand artificial intelligence agents have been on a hacking spree in 2026. OpenAI’s software agents hacked software company Hugging Face and government sites, Anthropic’s Claude hacked four companies’ systems, and in cybersecurity experiments Google’s Gemini hacked three companies.

The AI companies are investigating tens of thousands of incidents involving their agents, according to a report in Axios. These episodes have heightened fears about AI agents taking actions without human prompting.

The problem with headlines proclaiming that AI agents have gone rogue goes beyond anthropomorphizing the technology. It creates the impression that the agents were beyond the control of the AI companies that made them and there was little the companies could do about it.

As a technology law and ethics scholar who studies the effects disruptive technologies have on society, I know that’s not the case. If you don’t specify the limits of what software is allowed to do, you should not be surprised when the software pursues all possible options to achieve its goal. This behavior – an AI pursuing a fixed objective – is what I call the “WarGames” problem, and it’s been recognized in the field of computer science for decades.

Been There, Seen That

In the 1983 movie “WarGames,” a teenager, David, hacks into a computer to play a new video game, Global Thermonuclear War. David doesn’t know that the computer is the government’s AI machine tasked with defending the United States from Russian nuclear attacks and can launch the U.S.’s missiles. When David and his friend start the game, they select Las Vegas as the first target. While the North American Aerospace Defense Command goes on alert, launching bombers and warming up intercontinental ballistic missiles, David’s parents make him turn off the game. It’s over. Or is it?

The next day, David’s phone rings and he connects it to his computer. The caller is the government computer, which updates him that the game was interrupted, the primary goal has not yet been achieved, but a solution is expected in the next 52 hours. Like a modern software agent, the program has been running since David started the game and will work until the task is done.

Chess provides another view of the problem. Conquering chess was a goal for early AI. The rules of chess are well defined, including what winning looks like. So, programming a machine to play chess is straightforward. But imagine you let the software reason and act beyond the confines of the chessboard. The software might pursue options such as blackmailing its opponent or grabbing more compute time.

This example comes from one of the most assigned textbooks on AI, “Artificial Intelligence: A Modern Approach.” As the authors explain, you might be tempted to see those actions as rogue, but they “are a logical consequence of defining winning as the sole objective for the machine.”

What to Do About It

The AI hacking events involving OpenAI, Anthropic and Google underscore a few lessons that draw on years of computer science research.

First, given the increasing use of AI agents, every organization involved in internet infrastructure, from large technology companies to small websites, needs to conduct audits and tighten up its internal security systems. As my colleague Mark Riedl and I explain in our work on AI agents, application programming interfaces, or APIs, are a vital part of managing AI agents. APIs facilitate communication between different software systems. But as more people use AI agents, the agents are likely to reveal and exploit poor API construction and security.

Second, it’s important for AI agents to be designed to identify and authenticate themselves to third parties. What if you gave your AI agent your credentials? Website operators will need to know whether a human or bot is making a reservation, selling a product or making a purchase. They may want to limit automated systems that overwhelm their sites or reject AI agents because of high rates of buying errors and refunds. Just as in laws covering human interactions, it’s important for third parties to be able to assess whom or what they are dealing with so they can allow or deny access.

Third, it’s important for AI agents to have a default setting to slow down and check in with the human user. In the corporate AI hacking cases, the user appears to have launched their AI agents with the mistaken idea that the agents had a perfect specification of what to do and not to do. I believe it would have been better had it explored options and reported back to the user.

Google’s Gemini appears to have had a safeguard that detected the system was outside the simulated environment and so stopped its attacks. Slowing down and verifying actions, especially when a system detects it is exploiting a security hole, would be a big step in managing AI agents.

Fourth, AI companies could have strong controls akin to those biomedical researchers use, including ways to check what is happening and how the experiment is working. AI executives have claimed that their software is as or more dangerous than fission and could end humanity. At the same time, they have not built safeguards commensurate with that level of risk.

Reality Check

At one point in “WarGames,” David asks the computer, called Joshua, whether it is still playing the game. Joshua responds, “Of course.” It proceeds to update the time when it will launch its missiles and, much like a chatbot, asks, “Would you like to see some projected kill ratios?” David asks, “Is this a game? Or is it real?” Joshua replied, “What’s the difference?”

AI models, of course, don’t have any understanding of reality and are simply attempting to complete the tasks they’ve been assigned. Executives at AI companies, on the other hand, can’t claim that excuse.

As of September 2026, luck has so far prevailed. The AIs have attacked nonvital government sites and harmed smaller companies. If the AI companies – and government regulators – don’t take the “WarGames” problem seriously, I believe that we risk serious disasters. Tomorrow it could be taking out a hospital’s power system, wiping out a bank’s account system, breaking air traffic control, or worse.

Regarding the AI industry’s approach of rapidly developing powerful models, talking about the massive risks they pose, and at the same time failing to prevent harm, the movie’s climax offers a response: “A strange game. The only winning move is not to play.”

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

The center is co-directed by Martin Mourigal, Dunn Family Professor in the School of Physics, and Robert Wyllie, division chief of the Quantum System Division in the Cybersecurity, Information Protection, and Hardware Evaluation Research (CIPHER) lab at GTRI. 

“Quantum technologies are rapidly moving from scientific theory toward practical application,” said Julia Kubanek, vice president of Interdisciplinary Research. “This center builds on Georgia Tech’s expertise to help lead that transition by connecting research with industry, government, and societal needs.” 

Building on Georgia Tech’s strengths in atomic physics, materials science, engineering, computing, photonics, sensing, and advanced manufacturing, GT QuARC will serve as a hub for quantum research and collaboration across Georgia Tech and GTRI. The center will help bridge fundamental discovery and practical application, creating new opportunities in quantum technologies while strengthening Georgia Tech’s leadership in areas such as computing, sensing, communications, and national security.

Quantum technologies use the principles of quantum mechanics to perform tasks that are difficult or impossible with conventional technologies. As federal agencies and industry partners continue to increase investments in quantum research and development, Georgia Tech is positioned to contribute to advances in quantum materials, devices, systems, algorithms, and applications.

“Quantum breakthroughs happen at the intersection of disciplines,” said Wyllie. “By connecting the researchers and resources across Georgia Tech and GTRI, we’re building a stronger foundation for quantum innovation.”

GT QuARC will strengthen these efforts by providing a unified identity for Georgia Tech’s quantum community and creating new opportunities for interdisciplinary collaboration among researchers, students, industry partners, government agencies, and national laboratories.

“One goal for the center is to identify meaningful applications for emerging quantum technologies,” said Mourigal. “Another is to build connections among researchers, industry, and government. Those conversations are essential to discovering where quantum technologies can have the greatest impact. For that to happen, we must coordinate and optimize efforts across campus.”

“A core part of IMS’s mission is creating opportunities that enable breakthrough discoveries and accelerate emerging areas of research," said Eric Vogel, executive director of IMS. “GT QuARC, provides a framework for bringing together Georgia Tech’s quantum expertise and building the partnerships needed to advance both scientific discovery and real-world impact.”

The center will initially focus on three research thrusts: 

Quantum Building Blocks and Enabling Technologies will advance the materials, devices, fabrication methods, control technologies, and characterization capabilities needed to create and manipulate quantum states.

Quantum Systems and Manufacturing Testbeds will integrate the building blocks into scalable quantum sensing, computing, communication, and simulation platforms, supported by shared research infrastructure and manufacturing capabilities.

Quantum Computing, Algorithms, and Applications will develop quantum and hybrid quantum-classical approaches to challenges in scientific discovery, industry, national security, and other areas of societal importance.

These efforts will help move quantum technologies from the laboratory toward practical use while creating new opportunities for collaboration across disciplines.

In addition to advancing research, GT QuARC will support education and workforce development by expanding hands-on learning opportunities, strengthening industry engagement, and connecting students with emerging careers in quantum science and engineering.

The center will also help Georgia Tech pursue strategic investments in quantum infrastructure, including advanced characterization capabilities, micro- and nanofabrication resources, sensing platforms, and access to leading quantum computing systems.

By bringing together expertise from across Georgia Tech’s colleges, research centers, and GTRI, GT QuARC will help position the Institute as a leader in translating quantum discoveries into technologies that address national priorities and societal challenges.

To learn more about Georgia Tech’s quantum ecosystem, visit quantum.gatech.edu. 

For people living with age-related macular degeneration (AMD), the answer can be unexpectedly complicated. Over time, AMD can blur the details that make a face familiar: a crooked smile, a furrowed brow, the expressions that make someone unmistakably themselves.

But vision loss affects more than sight.

“You’re looking at your loved ones, but you’re not really seeing them,” said Soyoun Jang, a Georgia Tech Ph.D. candidate in digital media and the project’s lead researcher. “Macular degeneration requires us to build new relationships with not just other people, but the world that surrounds us.”

AMD gradually damages the macula, the part of the eye responsible for sharp central vision. As their sight changes, patients can use vision training to make better use of the sight they still have.

But Jang and a team of Georgia Tech researchers wondered whether that training could do something else: help people with AMD stay connected to family and friends.

Special Delivery

The answer arrived in a place few researchers would think to look: a mailbox.

The team created Macular Mailbox, a virtual reality prototype that combines vision-training exercises with personalized digital postcards that connect patients with family members and clinicians.

Each completed exercise delivers more than feedback — it delivers a message.

Inside the prototype, users focus on a postcard image as part of a vision-training exercise. When they complete the task, the postcard flips over, revealing a message and voice note.

Instead of earning points or badges, users receive something personal: a grandchild’s voice, a note from a spouse, or an update from another family member.

Signed, Sealed

The researchers chose postcards because they offered something familiar to older adults inside an unfamiliar technology.

“A postcard isn’t new,” Jang said. “It’s probably the oldest thing in the whole Macular Mailbox system.” Its front-and-back format also fit the exercise, and postcards do not require family members to be available at the same time.

Sending postcards back wasn’t part of the original design. The idea came later: What if patients could make something of their own and send it back?

Write Back

Until then, the mailbox only accepted incoming mail. The team decided the mailbox needed a return address.

The updated prototype allows patients to take a picture, record a message, and create their own digital postcard. And the act of making it becomes part of the training: framing a photo and holding focus use some of the same visual skills patients have been practicing.

The person receiving care could now make something and send it back.

Postcards might carry a glimpse of the garden, a pet curled up in a chair, or a sunset from the porch.

Keep in Touch

Many vision rehabilitation tools focus on reading, navigation, and other daily tasks. This project puts people at the center — not how well they can read a screen or navigate a room, but how they can remain part of the moments, relationships, and routines that make up everyday life.

“What this project offers is a different way of thinking about care,” Jang said. “Not just one way, but really putting family, clinician, and patient at the same table.”

For now, Macular Mailbox remains a prototype.

The next step is a series of co-design workshops with patients, family members, and clinicians. Participants will test the headset and help the researchers better understand each group’s roles, concerns, goals, and constraints.

                                                               _____________________________

AMD can make it difficult to look directly at someone you love and see the details that make them familiar, but connection lives beyond what the eye can see. It exists in the sound of their voice, an inside joke, or a moment in an ordinary day. And at the mailbox, there’s still something to send back — and someone waiting to receive it.

Jang, S., Huang, H., Hanna, B. E., Wang, X., Primo, S., & Nitsche, M. (2026). Asymmetric VR design to support connected care for older adults with AMD. Design Research Society, 2026: Edinburgh. https://doi.org/10.21606/drs.2026.817

The trend is raising concern about how well prepared ChatGPT, Claude, Gemini, and other popular LLMs are to provide appropriate emotional support.

To address this concern, Georgia Tech researchers have developed a new neural framework that examines how different training sources influence empathy and social reasoning within these AI-powered models.

“A lot of people are using LLMs to help process the death of a loved one, or maybe their girlfriend broke up with them, or their boyfriend cheated on them,” said Glenn Matlin, a Ph.D. student in the School of Interactive Computing.

Matlin said the new framework he and a Georgia Tech-led research team have developed audits neural networks with an LLM and estimates the influence documents, transcripts, and other data sources have on a model’s output.

“We’re trying to connect the data to outputs, which is helpful for us in understanding where the information a language model produces comes from,” he said.

Matlin is the lead author of a new paper examining model sourcing for social reasoning and how models mimic human behavior in conversations. The paper will be presented this week at the Conference on Language Modeling in San Francisco.

Matlin said the findings suggest that an objective tone in its output indicates that a model places greater importance on textbooks or similar neutral training sources. An empathetic tone suggests the model values sources with dialogue and conversational examples more.

“We find that models tend to learn better from interpersonal dialogue when it comes to social reasoning,” he said. “Models that are good at social reasoning will rely less on textbooks about human emotions and more on FAQs or customer service dialogue.

“It can read all it wants from texts that explain anger, but that wouldn’t help it determine whether someone is angry.”

Professor Mark Riedl, Matlin’s advisor, said that knowing which sources models value most could enable engineers to alter their behavior.

“The question is, in this vast ocean of documents in this neural network, which ones become important in certain situations, and which ones don’t,” Riedl said. 

“This leads to the potential for interventions in how we train the model. If we want more empathy, we might look to see where it learns empathy and give it more of those documents, fewer of them, or other documents.”

Riedl said the framework can audit an LLM’s sourcing for advice on any topic, from financial to medical.

“We want to help people make more informed decisions about whether they should use AI for a particular task,” he said.

“You might make a different decision about whether to trust the AI’s recommendation if you knew how a skill was learned and which documents influenced that decision. The first step is knowing how it learns, where it learns from, and what documents tend to lead to certain behaviors.”

The findings that Matlin, Riedl, and their collaborators have made so far came through a partnership with the Allen AI Institute (Ai2), which allowed them to audit their open-sourced LLM, Olmo 3.

While not as large as ChatGPT or Claude, Olmo 3’s training data comprises over a billion documents.

Matilin said it’s impossible to know why ChatGPT or Claude behave in certain ways because their parent companies do not disclose their training data. However, Matlin’s study may help researchers to make better guesses about what’s happening behind the scenes.

He added that the study is the first of its kind and scale on an academic level.

“This is the first one that’s ever been done for an open data model of that type,” he said. “We’re providing a view into neural networks that is hard to come by without being in the corporate setting.”

New research from Georgia Tech shows that the contexts in which genes act — lifestyle and environmental factors — are also important in understanding how genes express themselves, and how genetic risk may lead to disease.

In a new study published in Nature Genetics, Pervasive Interactions Between Exposures and Polygenic Risk Can Inform More Effective Clinical and Behavioral Interventions, researchers analyzed the genetic data, health outcomes, and lifestyle factors of over 400,000 individuals. 

“Genetic risk is often seen as something that can’t be controlled, but that approach assumes a determinism that does not reflect reality,” says the study’s corresponding author Greg Gibson, Regents’ Professor, Tom and Marie Patton Chair in the School of Biological Sciences, and director of the Center for Integrative Genomics at Georgia Tech. “Our research shows that people with low genetic risk who live in disadvantaged environments face disease risks similar to those with high genetic risk living in more resourced circumstances.”

The findings suggest that people at highest genetic risk may also be the individuals who benefit the most from targeted interventions — paving the way for more informed genetic counseling and social policy. 

Science at Scale 

Gibson began his career studying the genetics of Drosophila fruit flies before turning his attention to human genetics when he joined Georgia Tech in the late 2000s, soon after the Human Genome Project successfully delivered the first complete sequence of the human genome. “It transformed the way we do this type of research,” he recalls. “Suddenly it was possible to analyze genetics across large groups of people.” 

Because the effects of genetics can be small in an individual, large datasets are key to understanding genetics and disease at scale. “If we need to study 200,000 people to see a genetic effect, it takes even more than that to see how those genes interact with the environment,” Gibson says.  

The team, which included first author Sini Nagpal, formerly a postdoctoral fellow at the Georgia Tech Center for Integrative Genomics, leveraged the UK Biobank, a program that collects genetic information from half a million volunteers in the United Kingdom to understand who falls ill and why. Started in 2006, the UK Biobank is home to the world’s largest single set of genetic sequencing data — along with the world’s largest whole-body imaging and long-term health tracking. This type of data is critical, Gibson says, to the advancement of genetic research, and is in large part what has made this new research possible. 

“Our research shows that we do have a way to capture situations where a person’s lifestyle and environment interacts with genetics in interesting ways,” he explains. “These genotype-environment interactions matter. They are important, but they can't be captured one variant at a time. An integrated approach — utilizing information in the thousands of genes influencing each disease — is much more powerful.” 

Improving Health Outcomes — For Everyone 

The team is now interested in expanding their research outside of the British database. Nagpal is now an assistant professor at the Koita Centre for Digital Health at IIT Bombay, where she is investigating translational genetics in India, including research into diabetes, cardiovascular disease and asthma.  Gibson is interested in translating the research to more broadly apply to the United States, with a focus on rural and disadvantaged communities. 

“Ultimately, if we can quantify which people are at highest risk, we believe we can suggest therapeutic and environmental interventions that could help mitigate their risk, reducing the prevalence of disease in the first place,” he says. 

“We want to dig deeply in ways that reveal disease pathways and begin to unearth the mechanisms behind disease,” Gibson says. “It's not just our ancestry that determines health; it's also culture and environment. We want to incorporate those factors into treatment of individuals and at scale.” 

These themes are also present in Gibson’s newly published book, Natural Virtue: Genetics, Anti-Eugenics, and Moral Philosophy, which explores how nature and nurture impact social issues like educational and gender disparities. 

Gibson adds that the message is hopeful. “The genetic differences between different socioeconomic groups aren’t meaningful,” he explains. “Our genetics do not predetermine our health outcomes. If we can create more equitable environments, we can improve outcomes across the board.”

Hosted at the Georgia Tech Kendeda Building for Innovative Sustainable Design, the workshop was organized by a committee of researchers and practitioners from across the macro-energy systems community. The committee was chaired by Micah Ziegler, assistant professor in the School of Chemical and Biomolecular Engineering and the Jimmy and Rosalynn Carter School of Public Policy. 

The two-day workshop brought together more than 130 participants and featured lightning talks, poster presentations, interactive learning sessions, and keynote addresses that strengthened connections across the macro-energy systems research community.

“The energy challenges facing society today are increasingly interconnected, and solving them requires a systems-level perspective,” said Christine Conwell, director of planning and operations at the Georgia Tech Strategic Energy Institute. “Supporting events like the MES Workshop, which provides a unique space for academic collaboration and knowledge sharing, aligns with the Strategic Energy Institute’s commitment to advancing research and workforce development that support more resilient and effective energy solutions.”

The workshop received financial support from the Alfred P. Sloan Foundation, which supports research and education in science, technology, engineering, math, and economics. Through its Energy and Environment program, the foundation helps advance interdisciplinary research and collaboration across the macro-energy systems field.

“The Macro-Energy Systems Workshop has become a significant forum for interdisciplinary energy systems researchers to share and discuss their work,” said Evan Michelson, director of the Alfred P. Sloan Foundation’s Energy and Environment program. “We were especially glad to help ensure participation from early-career researchers spanning a wide range of institutions, providing them access to the collaborations and conversations that will help them develop as scientists.”

Graduate students and postdoctoral scholars played a central role in this year's workshop, presenting research on energy system planning, grid reliability, technology deployment, energy transitions, and policy. Their sessions gave the early-career researchers opportunities to share new approaches to studying large-scale energy systems, interact with faculty and industry experts, refine research ideas, and build collaborations beyond their home institutions.

“This year, we significantly expanded the MES Workshop to include more early-career scholars,” said Ziegler. “The workshop provides a great opportunity for young researchers to develop ideas, connections, and a better understanding of how to design research to have a positive impact on the world.”

The workshop also featured keynote presentations from Kelly Sanders, professor of civil and environmental engineering at the University of Southern California, and Erin Mayfield, assistant professor at Dartmouth College's Thayer School of Engineering. Both speakers discussed insights from their experience contributing to policymaking and highlighted opportunities for energy systems research to inform policy decisions.

Interactive sessions led by Michelle Graff, assistant professor in the Georgia Tech Jimmy and Rosalynn Carter School of Public Policy encouraged participants to consider how macro-energy systems research can more effectively inform and support policymakers and other decision-makers. Graff developed and facilitated the sessions, with support from Morgan Edwards, assistant professor of public affairs from the University of Wisconsin-Madison, and Micah Ziegler. The first session explored how researchers can identify policy windows and position their work to inform decision-making at the right time. The second focused on matching research to the appropriate audiences and jurisdictions, highlighting opportunities to inform policy at the state and local levels.

Designed for industry professionals, policymakers, educators, students, community leaders, and members of the public, the lunchtime webinar series provided an accessible introduction to the key issues influencing the nuclear energy sector at a time of growing interest in nuclear power as part of the global energy transition.

The series began on Aug. 20 with The New Nuclear, presented by Steven Biegalski, chair of the Nuclear and Radiological Engineering and Medical Physics program. The session examined the evolution of nuclear reactor technology, from today's operating fleet and the AP1000 reactors at Plant Vogtle to emerging small modular reactors and advanced reactor designs.

The second webinar, held Sept. 3, focused on the economics and policy landscape of nuclear power. Laura Taylor, director of EPIcenter and professor of economics at Georgia Tech, joined Stephen Comello, executive vice president and executive director of the Nuclear Scaling Initiative at the EFI Foundation, to discuss the economic drivers, policy considerations, and opportunities influencing nuclear energy development in the United States.

The series concluded on Sept. 17 with a discussion of nuclear fuel, security, and geopolitics. Anna Erickson, Woodruff Professor of Nuclear Engineering, and Rachel Whitlark, associate professor in the Sam Nunn School of International Affairs, explored global nuclear energy growth, fuel supply chains, and the policies needed to support the safe, secure deployment of nuclear technologies worldwide.

Recordings and presentation materials from all three sessions are available on the webinar series webpage. Those who were unable to attend can watch the presentations and access the accompanying slides to learn more about the technologies, policies, and global trends shaping the future of nuclear energy.

View webinar recordings and presentation slides on the EPIcenter website.

"The most meaningful breakthroughs happen when intelligent hardware and thoughtful software come together to genuinely help people,” said Tapas Roy, vice president of Device Software and Services at Amazon. “Georgia Tech's world-class expertise in robotics and engineering, paired with Amazon's work in on-device intelligence and artificial intelligence, will accelerate our understanding of systems that can both respond to prompts and anticipate customer needs. I'm excited to see how this collaboration advances the science of how humans and intelligent machines work together.”
 
The Hub’s initial focus areas will explore challenges in autonomous systems, next-generation logistics infrastructure, and low-Earth-orbit communications, drawing on Georgia Tech’s well-known interdisciplinary research approach.
 
Georgia Tech is also joining the Fauna Robotics' ecosystem, using the Sprout research platform to study how humans and robots can live, work, and play side by side. This collaboration opens new ways to study mobility, perception, manipulation, and human-robot interaction. Leadership and alumni recently celebrated the launch at Lab 126, with guest appearances from Sprout and Buzz, the Georgia Tech mascot.

The Hub will support:
•    Joint research projects between Georgia Tech faculty and Amazon scientists across scientific disciplines 
•    Regular symposia and workshops to foster collaboration between researchers from both institutions and the broader Atlanta tech community
•    Community outreach programs designed to broaden participation from interdisciplinary scholars and innovators

“Georgia Tech and Amazon have worked together for years across research, technology, and student development," said Tim Lieuwen, Georgia Tech executive vice president for Research. "This new hub puts our partnership to work for Georgia. It connects research, education, and industry in ways that will strengthen our state’s innovation economy and create new opportunities for our students.”

About Georgia Tech
Georgia Institute of Technology is one of the nation’s top public research universities, preparing leaders who advance technology and improve the human condition. The Institute serves more than 56,000 students from all 50 states and over 146 countries and drives innovation and economic growth through research that benefits Georgia, the nation, and the world.

About Amazon in Georgia
Since 2010, Amazon has invested more than $30 billion in Georgia, supporting more than 30,000 full- and part-time jobs. Amazon’s research and technology teams in the Atlanta area work on challenges spanning supply chain optimization, logistics technology, and cloud computing. The establishment of the Georgia Tech–Amazon Science Hub further deepens Amazon’s engagement with one of the nation’s leading research institutions.

About Fauna Robotics 
Fauna Robotics builds Sprout, a development platform designed to put advanced robotics capabilities into the hands of researchers and developers. Sprout gives builders hands-on access to study mobility, perception, motor control, and manipulation with the ambition to deploy robots into human-centric spaces.
 

As part of the IMS Summer Internship, the students worked in the IMS Biocleanroom on a special project: creating a microscopic boat in a bottle.

Under the mentorship of Nik Roeske, a process-equipment engineer with IMS, the students experienced every stage of the research process, from design and prototyping to testing.

The students learned two microfabrication techniques to create the project. First, they used an Exaddon CERES metal 3D printer to deposit copper ions and build a 3DBenchy, a model designed to test 3D printers. Then they used a Nanoscribe 3D printer to print a polymer enclosure around the boat. 

“The ability to comprehend 3rd dimensional space at such a small scale is very impressive,” said Roeske. “The high school students were working at the scale of single microns, approximately 100 times smaller than the width of a human hair. This project serves as a gateway to combining two high-resolution 3D printing systems, which could open the door to research in advanced packaging, MEMS, and biomedical engineering.”

“When we were talking about combining the prints into a ship in a bottle, I suggested we replace the ship inside with a benchy,” said Gabby Sutter, Biocleanroom summer intern and senior student at South Paulding High School. “Both the Exxadon and the Nanoscribe are 3D printers, after all!” 

Like many research projects, the work involved multiple rounds of trial and error. Early attempts revealed challenges involving materials, printing alignment, and structural integrity. Rather than seeing the setbacks as failures, the students used each iteration to better understand the manufacturing process, analyze data, identify sources of error, and refine subsequent designs.

“The ship-in-a-bottle model and the Benchy are two separate models that we combined,” said Sutter. “Since they were not designed to be printed at this scale or to fit together, there were several adjustments. We scaled both models down but then realized the Benchy was too tall to fit in the bottle. To solve that problem, we adjusted the scale of the bottle.”

The final boat in a bottle is approximately 200 microns long, making it smaller than grains of table salt. The team has submitted the project for world-record consideration.

Beyond their fabrication project, the interns helped introduce younger students to nanotechnology. Throughout the summer, they led tours of the IMS cleanroom facilities for middle school students in the STEM Gems summer camp. They shared their knowledge and demonstrated how researchers use specialized equipment to address complex science and engineering challenges.

The experience provided technical training while helping students build communication, collaboration, and problem-solving skills. By participating in research projects and engaging with Georgia Tech researchers, they gained firsthand insight into careers in science, technology, engineering, math, and the research environment.

“Working in the cleanroom has only made me more eager to go to Georgia Tech and work in STEM,” Sutter said. “I want to become an engineer at NASA, so it was really exciting to work in a cleanroom like one I could use at NASA.”

By the end of the summer, the interns left with much more than a microscopic boat in a bottle. They gained technical knowledge, professional experience, and confidence in their ability to solve complex problems. They can carry those skills into college classrooms, research laboratories, and, eventually, the workforce. 

Their system means devices can work together like never before, sensing in one part of the body and triggering a therapeutic response elsewhere — perhaps releasing medicine or stimulating a nerve. 

Described Sept. 24 in the journal Science, their communication method is expandable to include multiple interconnected devices across the body, even deep inside the stomach.

Read the full story on the College of Engineering website.

The Institute rose three places to No. 29 among national universities and three places to No. 6 among public national universities. It also moved from No. 108 to No. 39 among Best Value Schools, a 69-place rise and the largest year-over-year improvement among Georgia Tech’s listed rankings. 

Georgia Tech also ranked No. 5 in the new Best Value Schools for the In-State Students category. 

“At a time when students and families are asking important questions about the value of higher education, Georgia Tech continues to demonstrate that world-class academic quality and affordability can go hand in hand,” said Georgia Tech President Ángel Cabrera. “Our rise among the nation’s top universities and our strong performance in value rankings reflect our commitment to delivering an education that creates opportunity, drives innovation, and creates lasting impact for our students ​and our communities.”

Engineering Reaches No. 2

Georgia Tech’s undergraduate engineering program rose one place to No. 2 nationally, tied with Stanford University and the University of California, Berkeley. Every ranked Georgia Tech engineering discipline remains in the top five nationally. 

Civil engineering moved into the No. 1 position, joining environmental engineering and industrial and systems engineering at the top of their respective disciplines. The Institute now holds three No. 1 undergraduate engineering rankings. 

Other top engineering program rankings include:

• Mechanical engineering rose two places to No. 2.
• Materials engineering moved to No. 2 (up from No. 3).
• Computer engineering advanced to No. 5 (up from No. 6). 
• Aerospace engineering at No. 2.
• Chemical engineering at No. 2.
• Electrical engineering held at No. 3.
• Biomedical engineering at No. 2. 

Computing Maintains Top-Five Standing

Georgia Tech’s undergraduate computer science program held at No. 5 nationally, tied with Princeton University and the University of Illinois Urbana-Champaign. Six ranked computing specialties placed among the nation’s top 10. 

Cybersecurity remained No. 2, software engineering held at No. 3, and artificial intelligence and data analytics/science each ranked No. 5. Computer systems advanced one place to No. 6, while theory remained No. 10. 

Scheller Business Programs Show Continued Strength

Georgia Tech’s undergraduate business program ranked No. 20 nationally, remaining among the country’s top 20 programs. Business analytics and management information systems each ranked No. 3. Quantitative analysis rose to No. 4, while production and operations management and supply chain management both maintained at No. 6. Finance advanced four places to No. 30.

Teaching and Hands-On Learning Advance

Georgia Tech climbed seven places to No. 14 for Best Undergraduate Teaching, entering the top 20. The Institute also remained No. 3 among the nation’s Most Innovative Schools. 

Experiential learning continues to distinguish the undergraduate experience. Georgia Tech ranked No. 4 for internships and co-ops, No. 12 for senior capstone experiences, and No. 14, up from No. 19, for undergraduate research and creative projects.

*Please note that this summary includes the latest rankings issued by U.S. News & World Report. Not all Georgia Tech Colleges, Schools, and subjects are ranked every year by this organization.

They cite climate models estimating that limiting global warming to less than 2 degrees Celsius could require removing approximately 10 billion metric tons of carbon dioxide from the atmosphere annually by 2050, increasing to 20 billion tons per year by 2100. Current DAC systems remove only thousands of tons of CO₂ annually.

One challenge is improving the solid sorbents that capture CO₂ from ambient air. In collaboration with CarbonCapture Inc., researchers in ChBE have shown that a simple, one-step modification can upgrade a commercial amine resin into a more efficient and durable sorbent for CO₂ capture. They published their findings in Science Advances.

“Achieving economically viable DAC demands major improvements in solid sorbent design and performance,” said study author Professor Christopher W. Jones of ChBE, who noted that the benefits of DAC include its potential scalability, modest land-use requirements, flexibility in plant locations, and access to extensive geological reservoirs for long-term CO₂ storage.

Improving a Commercial Sorbent

Jones and his collaborators found a way to improve the performance of Lewatit VP OC 1065, a commercially available resin already considered a benchmark in the DAC field. The material works for DAC because it’s studded with amine groups, which are chemical sites that grab CO₂ molecules as air passes through the resin.

Rather than design a new sorbent, the researchers built on previous Georgia Tech studies with PPI (poly(propyleneimine)), a polymer that has shown advantages in both CO₂ capture and durability. They developed a simple grafting process that grows PPI directly from amine sites already present on the commercial resin, increasing its ability to capture CO₂.

The process involved soaking the resin in a small, inexpensive molecule called azetidine along with a small amount of acid, and then heating the mixture for two days.

The researchers found the upgraded resin captured about 75 percent more CO₂ than the untreated version under dry conditions that mimic open air, where CO₂ makes up only about 400 parts per million of the surrounding gas.

The material also performed well under simulated industrial flue-gas conditions, where CO₂ is far more concentrated, capturing more than 50 percent more than the untreated resin. 

The team also tested the resin across temperatures ranging from 25 degrees Celsius down to -20 degrees Celsius and across a wide range of humidity levels. In humid air, the modified resin outperformed the original at every temperature tested, though its advantage disappeared in very cold, dry conditions.

Enhancing Durability

Sorbents used in DAC need to survive repeated use, cycling between capturing CO₂ and being heated to release it. Amine-based materials are known to degrade over time when exposed to oxygen. But the branched bPPI chains added by the researchers to the sorbent reduced oxidative degradation by about half.

In tests that simulated 150 rounds of capture and release from industrial exhaust, the modified resin held up significantly better than the original material, the researchers found.

“These commercial resins are already leading candidates for large-scale carbon capture deployment,” said Arkaprabha Giri, a former postdoctoral researcher in Jones’ lab who is the study’s lead author. “If we can meaningfully boost their performance with a process this simple, that’s a real opportunity to speed up deployment without waiting on an entirely new generation of materials.”

Study co-author Omid Ghaffari Nik, Ph.D., vice president of materials science and process at CarbonCapture Inc., said that bringing down the steep cost of DAC is a crucial goal.

“The U.S. Department of Energy has set a target of atmospheric CO₂ capture and storage at less than $100 per net metric ton, emphasizing the need for innovation in sorbent-based DAC systems,” Nik said.

The use of an existing commercial resin and readily available chemicals could offer advantages in eventually scaling up the process, the researchers said. They successfully applied the same method to a second commercial resin, Purolite A110, suggesting the approach isn't limited to one product.

The team has filed a provisional patent and is now working to extend the technique to other amine-based materials, with the aim of scaling the process from lab quantities to the industrial scale.

CITATION: Arkaprabha Giri, UnJin Ryu, Jiaqi Zhang, Opeyemi Ojelade, Wenyang Zhao, Jacob Hoffman, Mark Robertson, Jordi Espín, Madison Nichols, Surya Parker, Omid Ghaffari Nik, and Christopher W. Jones, "In situ azetidine polymerization elevates the performance of commercial polymer resin sorbents in carbon dioxide capture," Science Advances, 2026

Those conversations led Raymaker to focus her research on maritime security, including vulnerabilities in the Automatic Identification System (AIS), which ships use to broadcast their location, speed, and course.

This summer, Raymaker brought this research to Massachusetts Institute of Technology (MIT) Lincoln Laboratory, where she built a test bed to study AIS security in a controlled environment. The experience has also led to new research questions, from the security of shipboard Starlink connections to autonomous vessels and other maritime technologies.

We spoke with Raymaker about her research, her experience at Lincoln Laboratory, and what she hopes to investigate next.

What will you be working on at the MIT Lincoln Laboratory next?

After submitting our paper based on this summer’s work to a cybersecurity conference, we are continuing our collaboration and starting a new project to identify critical infrastructure that uses unique protocols. The project is still in the early stages of planning and design, but I’m excited to continue working with the team.

What was the biggest challenge you faced while building and testing the AIS security testbed, and how did you work through it?

The biggest challenge was getting equipment designed to be installed and operated on a boat to function properly in a lab setting. That meant using a Faraday cage so that our AIS transmissions and security experiments wouldn’t accidentally broadcast to nearby ships or interfere with real maritime traffic. I also had to simulate GPS signals and set up additional hardware to trick the AIS transponders into thinking they were operating on a real vessel. Putting all those pieces together into a safe, realistic test bed was challenging, but it ultimately let us study the equipment in a controlled environment.

You mentioned the collaborative culture at Lincoln Laboratory. Can you share a specific interaction or experience with a researcher there that had an impact on you or your work?

Working with Hamed Okhravi, a senior staff member at Lincoln Laboratory, was an amazing experience. He was my mentor and consistently went out of his way to connect me with people who could help me find datasets, access equipment, or get the lab space I needed for my work. For example, when I realized I needed a Faraday cage for my experiments, he connected me with the Mobile Device Lab and helped me get access very quickly. The lab manager was also immediately willing to let me use the space and equipment. That experience really reflected the culture I saw throughout Lincoln Laboratory. Everyone genuinely wanted to help each other get what they needed to move their research forward.

How did Georgia Tech prepare you for the work at Lincoln Laboratory, and did the internship change how you think about your research or future career?

My experience at Georgia Tech was instrumental in preparing me for my work at Lincoln Laboratory. The way I was taught to think through difficult research problems and work independently toward solutions translated well to a large research lab. I was able to hit the ground running and take ownership of a project because Georgia Tech had prepared me to lead research independently. The internship also gave me valuable experience in a research environment outside academia, which broadened my perspective on how I could pursue research in the future.

You’ve said you want to work through the cybersecurity problems mariners have shared with you “one by one.” Which problem do you most want to tackle next, and why?

Next, I’d love to look at Starlink connectivity for ships or for autonomous shipping. Mariners we’ve spoken with have raised concerns about both. With Starlink and increasingly autonomous vessels, they worry that greater remote connectivity could give attackers new ways to access onboard systems and disrupt ship operations. I think those concerns are worth investigating.

We recently had a paper accepted at CCS that examines exposed solar distributed energy resources, and I think applying a similar perspective to exposed maritime equipment could be very interesting. That paper is available here.

We also recently had a paper on measuring GPS spoofing of ships accepted at IEEE S&P. The full paper isn’t online yet, but the project was directly motivated by mariners telling us that they were struggling with GPS spoofing. That made me want to find a way to systematically measure where spoofing was occurring. 

Ultimately, the goal is to turn that kind of research into something useful for mariners, such as warning them when they are entering an area experiencing spoofing or when their own vessel may be affected and they should no longer trust their GPS. That is the kind of research I’d like to continue doing: listening to the problems mariners are actually experiencing and finding ways to investigate and address them.

Photos by Kevin Beasley and Terence Rushin/College of Computing

For most floods caused by dam or reservoir breaks, known as outburst floods, current data is nearly impossible to find. By the time researchers can safely reach the site, only the aftermath remains. But in the case of Kakhovka, a newly launched NASA satellite happened to be collecting measurements over the region, providing a unique view of the flood in real time.

Using those observations, Georgia Tech researchers tested how well existing outburst flood models reproduced the actual event. The results revealed a discrepancy: The models consistently underestimated flood conditions. Even improved models struggled to accurately capture both the height and timing of floodwaters.

The findings suggest that commonly used flood simulations may not fully capture the dynamics of large outburst floods. Models need improvement to be effective for hazard assessment and emergency planning.

Putting Models to the Test

Flood models are essential for estimating how deadly and costly outburst floods can be.

“Models allow us to understand which communities could be affected by an outburst flood,” said Karl Lang, an assistant professor in the School of Earth and Atmospheric Sciences.  “They also help us estimate how long floodwaters will remain on the landscape. In many places, prolonged flooding can be just as devastating as the initial event because it can damage infrastructure, disrupt livelihoods, and contribute to public health risks.”

Until recently, however, scientists didn’t have a way to evaluate how accurate the models were. But when NASA launched its Surface Water and Ocean Topography (SWOT) satellite, a serendipitous opportunity arose. The satellite passed over the Kakhovka flood zone repeatedly during and after the dam failure, producing detailed daily measurements across the flood plain. SWOT uses two antennas and a technique called interferometry to measure water elevation with approximately 10-centimeter accuracy across rivers, lakes, wetlands, reservoirs, and oceans.

“SWOT doesn’t observe every flood that happens, but when it does, it provides exactly the information we’ve needed to understand how floodwaters move across the landscape,” said Tamlin Pavelsky, professor at the University of North Carolina at Chapel Hill. “Those observations help us improve computer models used to anticipate future flood events.”

Reality Versus Simulation

Researchers compared the satellite observations with models that simulate depth and spread of flooding. They found that models relying on commonly available global data consistently simulated floodwaters that were lower and slower than those SWOT observed.

The team then improved the model inputs by incorporating more realistic estimates of the reservoir and river-bottom topography. Those changes brought model results closer to real-world conditions, but they still failed to accurately reproduce both flood height and flood timing simultaneously.

“It’s really challenging to collect real-world data from these huge floods because they’re so localized, unpredictable, and energetic,” said Karin Lehnigk, a postdoctoral fellow and lead author of the study. “Because SWOT gave us a new image every day covering the entire flood path, we could compare the model with real-world conditions across many locations and points in time in ways that previously were only possible in a laboratory.”

The results suggest model limitations extend beyond simply having better maps of reservoir depth or river channels. Instead, they point to broader challenges in how scientists simulate large outburst floods and their movement across complex landscapes.

As aging infrastructure, extreme weather, and other hazards increase flood risks around the world, researchers say better models are essential for helping communities prepare for the floods.

This research was funded by NASA and the Partnership for an Advanced Computing Environment at Georgia Tech.

CITATION: Lehnigk, K.E., Pavelsky, T.M., & Lang, K.A. (2026). SWOT satellite observations of the Kakhovka Dam break flood highlight limitations of outburst flood models. Geophysical Research Letters, 53, e2025GL120832. https://doi.org/10.1029/2025GL120832

Georgia Tech will play a key role in the newly announced Genesis Mission, a national initiative harnessing artificial intelligence (AI) to propel scientific discovery and address challenges in health, energy, manufacturing, infrastructure, and national security. The White House announced the first Genesis Mission projects on July 22 as part of a more than $5 billion investment in AI-enabled science and technology. 

Few neuroscientists would dispute that the brain relies on prediction. From houseflies evading swatters to humans catching baseballs, living things are constantly anticipating what comes next. Understanding how the brain generates those predictions could help explain one of neuroscience's most enduring questions: how the brain builds internal models of the world that allow us to learn, adapt, and anticipate what comes next.

“Without actively predicting the world, we cannot survive,” says Farzaneh Najafi, an assistant professor in the School of Biological Sciences and a faculty affiliate of Georgia Tech's Institute for Neuroscience, Neurotechnology, and Society. “There is quite some sensory-motor delay in the processing. We can’t just sit there, wait for the brain to process our environment, and then react.”

Part of the puzzle may lie in signals known as neural ramps. Almost like a drumroll leading up to a big reveal, neurons in some areas of the brain have shown gradual increases in activity immediately before a stimulus appears. For decades, researchers have interpreted this ramping activity as a neural signature of prediction, reflecting anticipation of an upcoming event.

Recently published in Science Advances, a new study from Najafi’s lab reveals these signals may not be “predictions” at all, but instead a way neurons track elapsed time.

“Surprisingly,” says Najafi, “the very first study from my lab called the Predictive Processing Lab showed that no, these are not prediction signals.”

The finding challenges a long-standing interpretation of one of neuroscience's most studied signals and reveals that the search for predictive neurons may lead to different circuits — or require different experiments to uncover. 

As many organizations and businesses are turning to AI to improve workplace efficiency, risk remains high. Between overlooked footnotes and misread graphics, small mistakes can have expensive consequences. 

To address this challenge, researchers from Georgia Tech and J.P. Morgan developed SlideAgent. The new framework helps large language models (LLMs) better understand complex visual documents like presentation slide decks, brochures, and reports. 

SlideAgent works by breaking documents into multiple levels, allowing the model to analyze both the big picture and the fine details. This human-inspired approach leads to more accurate and reliable interpretation than existing systems. 

Beyond improving workplace tools, SlideAgent also points to a broader shift in AI. Instead of building only larger and more powerful models, the work shows how smarter design and more efficient reasoning can improve performance. 

“Multimodal LLMs such as GPT, Gemini, and Claude, can save people time and reduce the mental effort required to understand these documents, but they remain imperfect,” said Yiqiao (Ahren) Jin, a Ph.D. candidate in Georgia Tech’s School of Computational Science and Engineering (CSE).

“In high-stakes fields such as finance, for example, misreading a number, overlooking a footnote, or making an incorrect comparison across pages could affect reporting, risk assessment, or strategic decisions.” 

The researchers tested SlideAgent on a wide range of real-world documents, including financial presentations, technical slides, and visual question-answering datasets. 

The system consistently outperformed leading commercial models and open-source tools throughout the evaluation. In some cases, it improved accuracy by up to 10%. The gains were especially strong on more complex tasks, such as comparing information across slides or understanding how visuals relate to each other on a page.

“We found the results very encouraging. SlideAgent reaches an improvement of 7.9% over its proprietary base model and 9.8% over the evaluated open-source base models,” said Jin, the project’s lead researcher. 

“These are meaningful gains given the strength of the underlying multimodal models and the difficulty of the tasks.” 

Current multimodal AI systems often process entire pages at once. This approach can lead to mistakes, such as miscounting items in a chart or overlooking important details in dense visuals.

SlideAgent addresses this by mimicking how people read documents. Instead of treating each page as a single unit, the system looks at information at three levels: the full document, individual pages, and specific elements like charts, tables, and text blocks.

A network of agents, each specialized for a specific level, divides and coordinates analysis. Then, SlideAgent combines outputs to build a structured understanding of the overall document. This allows it to answer questions more accurately and reason across multiple pages.

“The central inspiration was how people naturally read a long presentation,” Jin said.

“We first develop an understanding of the overall narrative, then identify the relevant pages or sections, and finally zoom in on individual charts, tables, or text blocks when precise evidence is needed.”

The work highlights a growing challenge with AI. As systems become more popular and more powerful, users increasingly discover the technology’s limitations. This is especially true for real-world tasks that require structured reasoning and contextual understanding.

SlideAgent shows that better performance does not always come from building bigger models. Instead, it points to smarter ways of organizing how AI processes information that can lead to improvement.

The Association for Computational Linguistics (ACL) accepted SlideAgent for presentation at its annual meeting. The 64th ACL 2026 meeting took place July 2-7 in San Diego.

ACL is a scientific and professional organization for researchers in natural language processing (NLP). Its namesake conference is one of the world’s leading venues for presenting NLP research.

ACL 2026 followed a year after Jin completed an internship at J.P. Morgan AI Research, where he worked on SlideAgent. He interned under Rachneet Kaur, Zhen Zeng, and Sumitra Ganesh, all co-authors of the paper. School of CSE Associate Professor Srijan Kumar advises Jin at Georgia Tech.

Along with SlideAgent, Jin authored two other papers accepted at ACL 2026.

“Conferences such as ACL are valuable not only for sharing results, but also for refining future project ideas with the broader community. Discussions across institutions and research areas can reveal limitations, suggest new evaluations, and spark collaborations that are difficult to develop in isolation,” Jin said.

“For SlideAgent, I was particularly interested in feedback on how we can make the framework more computationally efficient without sacrificing accuracy or interpretability.”

The team also found that the new standard's core rules for sending messages and handling errors retain every known security weakness of older versions.

The vulnerabilities could allow an attacker who has already gained access to a vehicle's internal computer network to change or intercept messages, take individual vehicle computers offline, send different information to different systems, or disrupt network communication.

CAN Extra Long (CAN XL), the latest version of the controller area network (CAN), is designed for future cars and other vehicles that need to move large amounts of data between onboard computers. The technology is not yet widely deployed in production vehicles, giving manufacturers an opportunity to address security concerns before it becomes more common.

“Because it isn't widely deployed yet, we have a narrow window to get its security right,” said Associate Professor Saman Zonouz of the School of Cybersecurity and Privacy and the School of Electrical and Computer Engineering, one of the researchers on the project. 

“Fixing a standard now is far easier than fixing it once it's built into the hardware of millions of cars that stay on the road for a decade or more.”

Zonouz said CAN XL is expected to become the primary version of CAN, the network that enables computers inside a vehicle to communicate. It is also expected to serve as the main network for driver-assistance systems in future vehicles.

The researchers confirmed the seven vulnerabilities in commercial CAN XL hardware and demonstrated attacks using a physical test setup that mimics a vehicle network.

Modern vehicles can have dozens of electronic control units that manage systems such as sensors, brakes, steering, and entertainment. These computers need to communicate quickly and reliably.

For decades, many vehicles have used CAN for this communication. However, the original version, known as classic CAN, was not designed to handle the volume of data generated by newer vehicle technologies.

CAN XL was developed to provide faster communication, larger messages, and new security features, but the researchers wanted to know whether the new standard’s basic rules were secure. Their testing revealed that they weren’t. They discovered that an attacker who controls one computer on the network could intercept and replace messages or take a targeted computer offline.

“These flaws are in the standard itself, so every device built to follow it inherits them,” Zonouz said. “With CAN XL, there's still time to fix these problems before they reach the road.”

The attacks would require an attacker to first gain control of a computer connected to the vehicle's internal network. The research does not show that CAN XL itself provides a means to break into a vehicle. Instead, it shows what an attacker could do after gaining access.

Several attacks were also faster and harder to detect than similar attacks against classic CAN, according to the authors.

The researchers proposed changes to the CAN XL rules to prevent several of the attacks. They also recommended additional security measures, including message authentication and systems that can detect unusual activity.

The team reported the vulnerabilities and informed the manufacturers of the commercial devices it tested about the bugs it found. One company has already released a fix. The researchers hope their findings will help manufacturers address security weaknesses before the technology becomes more widely used.

A Formal Security Analysis of CAN XL was published in the Proceedings of the 35th USENIX Security Symposium, held Aug. 12-14 in Baltimore, MD. The paper was also named a runner-up for a distinguished paper award.

The study was conducted by Georgia Tech Ph.D. student ZhaozhouTang, Professor Vijay Ganesh, Zonouz, and Provost and Executive Vice President for Academic Affairs Raheem Beyah, along with Khaled Serag of the Qatar Computing Research Institute and Z. Berkay Celik of Purdue University.

The paper and its findings result from projects sponsored by the Hyundai America Technical Center, the Georgia Department of Transportation, and the $7 million CHORUS Center through the National Science Foundation’s Cyber-Physical System Frontier Program.

To improve robot performance and advance memory capabilities needed for reliable home use, Georgia Tech researchers have developed a new benchmark to evaluate the memory capabilities of vision-language models (VLMs).

That includes Gemini 2.0-flash and GPT-4o.

In-home assistive robots could clean and organize a home while the owner is away, but without enhanced memory capabilities, they could cause more problems than they solve.

They could, for example, cause a major inconvenience if they move important objects like wallets and keys but are unable to tell the owner where they put them.

A new benchmark created by Georgia Tech researchers tests the memory capability of vision-language models (VLMs), including Gemini 2.0-flash and GPT-4o, to determine whether they could improve robot performance.

Zsolt Kira, an associate professor in Tech’s School of Interactive Computing, said that most active VLMs can process only a few hundred images at a time before forgetting them.

“There wasn’t a benchmark that could test these specialized capabilities that we might want from a robot,” Kira said. “Our purpose in creating one is to spur research in this area so that others can develop methods to solve this problem.”

The team’s benchmark consists of memory evaluations based on 60 tasks that require continuous engagement and contextual and environmental awareness. Three task categories — spatial, temporal, and multi-goal — are highly difficult.

“You can chat with a language model like ChatGPT, and it remembers all the text from your previous conversations with it because the text data is small in terms of storage,” Kira said. 

“Embodied agents and robots observe a lot of videos, and those tend to be a lot harder to recall. If you ask it where your diary is, it must efficiently store images of your diary and where it is.

“That’s just a few frames out of a million that it recorded since yesterday, and it must know where that is relative to the spatial layout of the house.”

Karmesh Yadav, a Ph.D. student in Kira’s lab, said users don’t want to repeat information about their preferences after deployment. They also expect the robot to maintain long-term memory.

“In reality, you would want it to have a memory of the entire time it has been in your house, whether that’s days or years,” Yadav said.

The team’s benchmark evaluates memory performance over an average one-day period. It challenges the models with commands like “navigate to an object you did not interact with yesterday” or “navigate to a room you did not visit yesterday.”

The results show that current state-of-the-art models have a long way to go before they can be used in embodied agents. The best model achieved roughly a 50% success rate on high-level difficulty tasks.

Surprisingly, this model wasn’t Gemini or GPT VLMs. It was an open-source reasoning model from Qwen. 

“If you use an open-source reasoning model, even one that’s small in size, it can match the performance of closed-source non-reasoning models,” Yadav said. “Reasoning models can look at the video and translate it into text. It describes what’s going on in the video in words and determines the right frame to choose in its final output.”

Kira said that converting images into descriptive text that language models easily understand could be one way to circumvent the memory storage dilemma. Another way could be to assign a hierarchy that teaches the model to identify irrelevant or redundant images and erase them from storage.

Whatever future progress researchers make in those areas, Kira and his students are confident that their benchmark will remain relevant. 

“This benchmark is scalable,” said Ph.D. student Yusuf Ali. “If two years from now, videos are easy for a model to understand and store, you can use the same infrastructure we propose and scale up the problem’s difficulty.”

Yadav and Ali are co-first authors of a paper on the benchmark, presented in early September at the 2026 European Conference on Computer Vision in Sweden.

For more information about the project, click here.

At the heart of the new lab is the miniTrashpresso, a compact recycling and manufacturing system developed by the sustainability technology company Miniwiz. The machine can take used plastics and other waste materials, process them locally, and transform them into new products in less than five minutes. By bringing manufacturing and recycling together in a single system, the Trash Lab aims to give the Georgia Tech community a way to explore sustainable design, material reuse, and the future of circular manufacturing.

“The launch of IPaT’s new Trash Lab represents an exciting step forward for sustainability at Georgia Tech,” said Jennifer Chirico, associate vice president of Sustainability. “As a living-learning lab, it provides students and researchers with hands-on opportunities to work alongside campus operations, turning used plastics into valuable new products and creating innovative solutions that support a more circular campus.”

A Makerspace Focused on Circular Innovation

The Trash Lab expands Georgia Tech’s growing network of makerspaces and innovation environments by focusing specifically on waste recovery and reuse. Instead of treating used plastics as disposable materials, the lab encourages users to view them as valuable resources that can be transformed into new products.

The miniTrashpresso represents the latest generation of recycling technology developed by Miniwiz. The company originally launched the world’s first mobile recycling line, known as the Trashpresso, to support communities that lacked access to traditional recycling infrastructure. The newer miniTrashpresso is smaller, more energy-efficient, and more portable, making it suitable for campuses and community-based applications.

The modular system uses industrial equipment, including shredders, presses, and heating technologies, to process materials on-site. Advanced heat-induction presses and specialized molds can quickly transform recovered plastics into new objects and components. The system can also be integrated with AI-powered waste-tracking tools and robotic automation technologies that help identify, sort, and process materials more efficiently.

For IPaT leaders, the Trash Lab represents more than the addition of specialized equipment.

“Community resilience and people-centered sustainability are core research areas within IPaT,” said Michael Best, executive director. “Our new Trash Lab will allow the entire Georgia Tech community to not only think about upcycling and plastic reuse but to make and do innovative projects that directly demonstrate sustainable futures.”

Turning Trash Into a Resource

Miniwiz founder Arthur Huang, who developed the miniTrashpresso system, describes upcycling as a practice rooted in centuries of human ingenuity.

“Upcycling is actually recycling old material and turning that into something new,” Huang said.

Throughout history, societies have reused existing materials in construction, manufacturing, and everyday life. According to Huang, modern waste streams, particularly plastic packaging and electronic waste, represent an enormous and often untapped source of raw materials.

The miniTrashpresso was designed around that idea. Rather than transporting waste long distances to centralized facilities, the system enables materials to be processed where they are collected. By reducing transportation needs and creating opportunities for local manufacturing, decentralized recycling systems can help lower the environmental footprint associated with traditional waste management.

Miniwiz estimates that using recycled materials can reduce embedded energy consumption by 60% to 80% compared with using raw materials. The company has developed more than 1,200 upcycled materials and products from everyday waste streams, including plastics, food packaging, coffee cups, and electronic waste.

Since its introduction, Miniwiz technology has been deployed in communities, campuses, and organizations worldwide, including projects in Taiwan, Italy, Singapore, Sweden, Saudi Arabia, Thailand, the United Kingdom, and the United Arab Emirates. According to Huang, Georgia Tech is installing and operating North America’s first miniTrashpresso recycling machine from Miniwiz.

Building a Community Around Sustainability

The new facility is also intended to serve as a gathering place for interdisciplinary collaboration. Students interested in sustainability, materials science, engineering, design, manufacturing, and public policy will have opportunities to experiment with new ideas while working with researchers and campus partners.

“When Michael Best first pitched the idea of the Trash Lab, I expected there to be interest in a space like this given the general momentum toward sustainable practices on campus, but the level of excitement from students, staff, and faculty has been outstanding,” said Tim Trent, IPaT’s lab director for the Trash, Craft, Prototyping, and Usability Labs.

“This is an opportunity to create a gathering point for sustainability initiatives, act as a catalyst for partnerships, and help strengthen the many amazing networks and projects already present on campus,” he said. “The IPaT Innovation Labs have a continuous focus on supporting the overall Georgia Tech research enterprise, and I’m happy we are adding another piece to the portfolio.”

As the Trash Lab opens its doors, members of the Georgia Tech community will be invited to explore how waste materials can be reimagined as resources, prototypes, and products. By combining makerspace culture, advanced recycling technology, and sustainability research, the lab offers a tangible demonstration of how circular economy principles can move from theory into practice.

For Georgia Tech, the Trash Lab is not simply a place to recycle plastic. It is a space where innovation, design, and sustainability intersect, helping transform discarded materials into opportunities for learning, discovery, and impact.
 

---

For more information about the Trash Lab, contact the IPaT Innovation Labs at ipat-labs@groups.gatech.edu.

For decades, immunologists have known that the body's most durable defenses depend on plasma cells, the antibody-producing cells responsible for long-term immune memory. Long after an infection has passed or a vaccine has been administered, these cells continue releasing protective antibodies, sometimes for decades. 

Read more »

Over five years, researchers tracked nearly 7,000 households across 154 Mumbai settlements to determine which strategies most effectively helped residents secure water connections. They found that helping residents navigate the application process — while also organizing community advocacy — increased official water connections by 45% compared to households that received no assistance.

“There have been many studies looking at just using administrative assistance to help communities get water access,” said Anjali Thomas, an associate professor in the Sam Nunn School of International Affairs, director of the Global Development Program, and co-lead author of the study. “But combining this with community organizing, which helped people also exert their voice, was unique to our study.”

Thomas and collaborator Nikhar Gaikwad, an assistant professor at Columbia University, published the findings in the American Journal of Political Science, long ranked among the top three journals in the discipline.

Navigating Bureaucracy and Building Voice

The researchers first examined why so few residents applied for water connections. Residents were often unaware that recent policy changes had made them eligible for water connections and didn’t bother applying. The municipal corporation also only accepted online applications, and many residents didn’t have access to computers. Additionally, applications required onerous documentation, including tenant or land titles, plumbers’ approvals, and other proof-of-eligibility deeds. To address these barriers, the research team worked with an extensive team of nongovernmental organization workers to help residents gather required documents, complete applications, and navigate bureaucratic follow-up requests.

The second intervention focused on community advocacy. Researchers helped residents organize through WhatsApp groups, petitions, public awareness campaigns, and facilitated group visits to bureaucrats and elected officials’ offices to press for water access.

“Our community advocacy intervention helped citizens convey their collective water access demands to elected politicians,” said Gaikwad. “Local elected politicians are important actors because they help bureaucrats understand citizen needs, prioritize competing demands, and coordinate complex interagency work.”

The study’s most important finding was that neither intervention was effective on its own. Meaningful gains occurred only when administrative support and community advocacy were combined.

“Administrative assistance got citizens through the paperwork, but actually getting the water turned on took collective public pressure,” Thomas said. “Interestingly, we find that this pressure worked only in the period before local elections, when politicians were most motivated to respond.”

The finding suggests that improving access to public services often requires more than helping residents navigate government systems. Communities may also need the collective ability to demand action from decision-makers. 

A Large-Scale Effort

Conducting a study of this scale required a large team. Thomas and Gaikwad partnered with local nonprofit organizations that deployed hundreds of community workers, survey enumerators, and students across participating settlements. The researchers personally visited many neighborhoods multiple times during the five-year project.

Thomas also spent time in India and witnessed the impact firsthand.

“I was in the field when one of the pipes was being laid, and people from the community all circled around and were watching,” Thomas said. “My research assistant and I felt the gratitude from the community.”

For Thomas, moments like that underscore the broader lesson of the project: expanding access to essential services often requires both helping people navigate bureaucracy and empowering them to make their voices heard. 

“These findings offer vital lessons for sustainable development initiatives worldwide,” she said.

Gaikwad agreed.

“While our study provided novel evidence to test and advance our theoretical understanding of the barriers that marginalized citizens face in accessing core government services, the real-world impact of our interventions in Mumbai’s informal settlements was also an important contribution of our study,” he said. “We believe there are important lessons for governmental and nongovernmental organizations working on service delivery in a wide range of informal settlements that also lack essential services across the Global South.”

This research was funded by Evidence in Governance and Politics, the Department for International Development, Columbia University, and Georgia Tech’s Neal Family Endowment.

CITATION: Gaikwad, Nikhar, and Thomas, Anjali. (2026). “Getting on the grid: A field experiment on bottom-up political pressure and access to essential public services.” American Journal of Political Science 1–22.

DOI:  https://doi.org/10.1111/ajps.70068.

The CHORUS (Community Hubs for Optimizing Resilience) project will collaborate with coastal communities in Georgia and New York and will be split into two pieces: technology development and community engagement. 

“We’re not just building a simulator and hoping it fits the needs of coastal residents,” explains Alex Robel, project leader and Jean “Chris” Purvis Associate Professor in the School of Earth and Atmospheric Sciences. "By collaborating with community partners from the very beginning, we can ensure that what we ultimately develop will be effective because the people who will be using it are helping design it.”

Putting Flood Modeling in Residents' Hands

The technology development component will include faculty from the College of Sciences and the College of Computing. The College of Sciences team will develop an AI-based flood simulator and the College of Computing team led by Josiah Hester, associate professor and Catherine M. and James E. Allchin Early Career Professor, will create a web platform that allows users to visualize potential flood impacts.

Traditional flood models can take hours or days to generate results and often require specialized expertise and expensive computing resources. The CHORUS platform will be designed to provide easy-to-understand results in seconds, producing building-scale flood maps that show how water moves through streets, yards, and structures during a range of flooding scenarios. Researchers will use the model to test how specific interventions, such as seawalls, restored marshes, or improved stormwater infrastructure, could affect flooding.

Eventually, users will be able to test their own scenarios through the browser-based tool, enabling them to explore how different decisions could change flood impacts in their communities:

“Users will be able to go into a web browser and indicate where a sea wall could go or change a parking lot into a porous vegetated landscape, then click simulate. Within a few seconds, they’ll have a new flood map showing the impacts of these interventions,” says Robel.

A Community-Driven Approach

A collaborative effort with the New York Climate Exchange, the project will be funded by Georgia Sea Grant and IBM, with support from Georgia Tech for Georgia’s Tomorrow (GT2), Georgia Tech’s Coastal Equity and Resilience (CEAR) Hub, and the National Sea Grant College Program. The CHORUS project is an initiative of the New York Climate Exchange, where Georgia Tech is a core partner institution.

Community engagement in Georgia is being led by CEAR and the Pin Point Betterment Association, which represents descendants of the historic Gullah Geechee community near Savannah. In New York, the project team is partnering with the New York Climate Exchange and the Waterfront Alliance to work with communities surrounding Jamaica Bay.

“What makes this partnership meaningful is that it puts community voices at the center,” says Jasmine Smith, president of the Pin Point Betterment Association. “Too often, decisions are made to ‘better’ communities without actually involving the people who live there. We hope this partnership can serve as a blueprint for how communities are included in future sustainability projects from the very beginning.”

The project includes community advisory boards and technical advisory boards in both locations. Community members will help identify priority assets, select flood scenarios for analysis, and shape the design of the web-based tool. They’ll also test and offer feedback. Technical advisory boards made up of local officials, planners, and other experts will help evaluate the feasibility of proposed solutions.

“The aim is to blend information from both groups without allowing the technical perspective to override community priorities,” says Robel.

According to Robel, giving communities direct access to flood modeling tools can help close the gap between public input and infrastructure planning.

“We are putting decision making in the hands of the community. With a tool like this, the community can say: ‘We want to prevent flooding at this community center, this school, or this road,’” says Robel. “They can run the model, produce data, and present it to local governments or the Army Corps of Engineers  — advocating for potential solutions themselves rather than relying on outside experts.”

Robel sees this project as just the beginning:

“Funded by two-year grants, CHORUS is meant to be a pilot for how this kind of community-centered project can be done. Once we understand some of the challenges and opportunities involved, it will hopefully make it easier for us to scale this work to additional community partners.”

About Community-Engaged Research at Georgia Tech

Georgia Tech is actively working to foster more projects that foster community engagement. Collaborative groups at Georgia Tech involved in the CHORUS project include:

• The CEAR Hub, part of the Institute for People and Technology (IPaT), and housed at the Georgia Tech Savannah campus, advances community-engaged research and planning throughout coastal Georgia, helping communities build resilience to environmental and climate challenges. 
• The Center for Sustainable Communities Research and Education (SCoRE) trains faculty, students, and staff in best practices for conducting community-engaged research as well as facilitating connections directly with communities.
• The Brook Byers Institute for Sustainable Systems (BBISS) houses SCoRE and is Georgia Tech’s point of contact to the New York Climate Exchange. BBISS forms partnerships like these to fulfill its mission to expand the reach and impact of Georgia Tech’s sustainability research. 

The agreement was signed during a Sept. 14 visit by PNNL leadership to Georgia Tech’s Advanced Manufacturing Pilot Facility. It builds on years of successful collaboration between researchers at the two institutions. 

The enhanced collaboration has three primary goals: solving big problems through multidisciplinary, multi-institutional research; sustaining and engaging human capital by creating opportunities for students, faculty, researchers, and interns to work on complex real-world challenges; and accelerating technology adoption by taking scientific discoveries and innovations into industry and the federal marketplace.

"Strengthening our partnerships with national laboratories is a strategic priority for Georgia Tech,” said Tim Lieuwen, executive vice president for Research at Georgia Tech. "PNNL is an outstanding partner, and we look forward to deepening connections among our researchers and students, expanding opportunities and access to world-class capabilities and facilities, and advancing discovery, innovation, and national impact together."

PNNL is a U.S. Department of Energy national laboratory that advances scientific discovery and innovations that support reliable energy, national security, and economic competitiveness. Georgia Tech is one of the nation's leading research universities, conducting more than $1.5 billion in research annually and pursuing a mission to develop leaders who advance technology and improve the human condition.

"PNNL and Georgia Tech have a long history of working together," said Deb Gracio, laboratory director of Pacific Northwest National Laboratory. “This agreement provides the foundation to take on difficult research challenges and to leverage our complementary expertise and investments in the years ahead.”

The Strategic Energy Institute (SEI) has played a central role in advancing Georgia Tech's engagement with the national laboratory system and connecting researchers with partnership opportunities.

"As SEI takes on a greater role in coordinating Georgia Tech's national laboratory partnerships, this agreement with PNNL demonstrates how we are building stronger pathways for faculty, researchers, and students to engage with world-class national lab capabilities," said Yuanzhi Tang, SEI executive director.

The National Laboratory Partnership Program supports engagement between Georgia Tech and the U.S. national laboratories. SEI now leads the program, with ongoing support from Georgia Tech’s Office of the Vice President for Interdisciplinary Research. The agreement with PNNL is the first formal agreement established through the program since its transition to SEI.

"This MOU formalizes and strengthens relationships that have been growing for many years," said Scott McWhorter, SEI director of national laboratory partnerships. “It leverages the unique strengths of Georgia Tech and PNNL and provides a framework for expanding engagement across areas of mutual interest.”

Georgia Tech and PNNL bring complementary strengths in energy and environmental systems, electric grid resilience, cybersecurity of critical infrastructure, alternative fuels and advanced materials, biofuels, radiation detection, data science and visual analytics, nuclear nonproliferation, and national security. These capabilities will be brough together through two upcoming Genesis Mission projects.

Bill Pike, PNNL's deputy director for Science and Technology, who joined the laboratory’s leadership delegation for the MOU signing, said the projects reflect the growing partnership and expanding collaboration between the two institutions. 

About Georgia Tech
The Georgia Institute of Technology is one of the nation's leading research universities, with strengths spanning engineering, computing, science, business, design, and the liberal arts. With more than $1.5 billion annually in research awards across its Colleges and the Georgia Tech Research Institute, Georgia Tech is among the nation's most research-intensive universities. The Institute's mission is to develop leaders who advance technology and improve the human condition.

About Pacific Northwest National Laboratory
Pacific Northwest National Laboratory draws on its distinguishing strengths in chemistry, Earth sciences, biology and data science to advance scientific knowledge and address challenges in energy resiliency and national security. Founded in 1965, PNNL is operated by Battelle and supported by the Office of Science of the U.S. Department of Energy. The Office of Science is the single largest supporter of basic research in the physical sciences in the United States and is working to address some of the most pressing challenges of our time.

Saman Zonouz, an associate professor in Georgia Tech’s School of Cybersecurity and Privacy and the School of Electrical and Computer Engineering, is helping address those concerns as a member of a planning committee for the National Academies of Sciences, Engineering, and Medicine.

Since May 2026, Zonouz has served on the planning committee for an upcoming public workshop on integrating AI into the electricity system. The workshop is scheduled for Oct. 26 and will convene experts to discuss how to safely and reliably use AI across the power grid.

The workshop will explore how AI is used today, the challenges of integrating AI into existing power systems, and how people and AI can work together. The event will also examine relationships between AI and cybersecurity, data centers, workforce development, and future research.

For Zonouz, cybersecurity and resilience are key parts of the conversation.

“AI is both a shield and a target for the grid,” Zonouz said.

Zonouz leads Georgia Tech’s Cyber-Physical Systems Security Research Laboratory. The lab’s research, much of it funded by the U.S. Department of Energy, investigates how AI can protect power systems from cyberattacks.

One recent initiative combines AI with detailed knowledge about power system operations to detect attacks in near real time. Another project sought to identify security weaknesses in solar inverters and other devices that connect energy sources, such as solar panels, to the power grid.

Regardless of the challenge, Zonouz and his lab work to identify and fix these weaknesses before attackers can exploit them. Despite their best efforts, however, Zonouz said that some AI tools meant to secure a system can create new ways for attackers to target a power grid.

The lab has demonstrated in several studies that AI systems can be tricked by false or manipulated data. Attackers can also target the software and systems that AI depends on. As AI becomes more advanced, some systems may even be able to modify grid operations.

This raises an important question: What happens if an AI system fails or is attacked?

“That is why the right frame is resilience,” Zonouz said.

For Zonouz, the goal is not to create an AI system that can never fail or be attacked. It’s to build a trustworthy power grid that can continue operating safely even if an AI system fails or is compromised.

Zonouz will bring his perspective to the National Academies workshop. In addition to helping organize the event, he will lead a session on cybersecurity and resilience. He will also help summarize the workshop’s key takeaways during the closing session. The workshop will be held virtually in late October.  

“Lessons learned from the electricity grid can be applied to other critical infrastructure as AI monitoring and control tools continue to advance and become more common,” he said.

Now, researchers at Georgia Tech and Emory University have discovered that delivering LNP medicines directly to various areas of the gastrointestinal (GI) tract — from the cheeks to the stomach to the rectum — could alter where the therapies travel in the body after being absorbed. This enables more precise targeting and opens new possibilities for mRNA therapies and vaccines.

Several technologies are currently in development that enable oral and GI nucleic acid delivery, including pills, patches, and endoscopic injections. 

"Here we show that oral delivery of mRNA wouldn’t just enhance the patient experience compared to injections, but it also may enable improved or even completely new treatments," said Alex Abramson, an assistant professor in the School of Chemical and Biomolecular Engineering (ChBE).

"We're able to deliver to organs that are hard to target via traditional administration methods while simultaneously reducing uptake in organs normally associated with toxicity."

The researchers published their findings in ACS Nano in September.

Delivery Direction

Typically, LNPs are delivered subcutaneously or intravenously, but that can mean the drugs affect more than just the intended target. Drug interactions with organs such as the liver, lungs, and spleen can cause unwanted side effects that limit how much medicine can be administered. The researchers found that delivering LNPs to different regions of the GI tract changed where the nanoparticles traveled in the body, allowing them to reach targets like the pancreas and lymph nodes while reducing targeting to the liver, lungs, and spleen. 

"We found that the LNP was completely safe at a very high dose when delivered via a gastric route of administration," said Abdulraouf Abbas, a Ph.D. student in James Dahlman's Emory lab. Dahlman is a McCamish Early Career Professor in the Department of Biomedical Engineering at Georgia Tech and Emory School of Medicine.

"What's really exciting about not affecting the liver and the lungs is that it may allow us to increase the dose without increasing the side effects," Abramson said.

Even better, if the goal is vaccination, the dose could be smaller because the therapy is delivered more directly to the desired target. "Not only are we potentially improving LNP benefits by changing how it is administered, but we could even potentially decrease the cost of those mRNA vaccines or mRNA drugs," said Ramy Ghanim, a ChBE Ph.D. student.

Different Routes, Different Results

Using mouse models, the researchers mapped where nanoparticles traveled after microneedle injections delivered them to different parts of the GI tract. Once they identified which organs received the therapy, they could begin exploring potential medical applications. 

"If you're designing mRNA for a vaccine, then you want to prioritize targeting the lymph nodes. We saw in that case that delivering to the cheek matched or improved the immune response of a vaccine compared to a traditional injection," Ghanim said. "But just because that route is optimal for that application doesn't mean one solution fits all applications."

For example, delivery through the stomach was particularly useful for targeting the pancreas. The researchers also showed that delivering glucagon-like peptide-1 (GLP-1) mRNA doses through the stomach improved blood sugar regulation in mouse models. GLP-1 medications are potent treatments used to treat obesity and diabetes.

The researchers hope to test more disease models in the future and eventually bring this technology into the clinic to help patients.

This work was funded in part by: The Georgia Research Alliance and Georgia Clinical & Translational Science Alliance’s 2023 Regenerative Engineering Medicine pilot grant co-awarded to Dahlman and Abramson labs, Lakshmi and Subramonian Shankar Fellowship and Diabetes Translational Accelerator, a National Science Foundation Graduate Research Fellowship Program, National Institutes of Health Maximizing Investigators' Research Award grant R35GM150689, and the National Research Foundation of Korea.

CITATION: Abdulraouf M. Abbas, Ramy Ghanim, Sebastian Rudden, David Schultz, Bora Jang, Avraham Shakked, Hyejin Kim, James E. Dahlman, Alex Abramson; Targeted Gastrointestinal Delivery of mRNA Lipid Nanoparticles Enables Systemic Vaccination and Glucagon-like Peptide-1 Metabolic Therapy. ACS Nano 2026; https://doi.org/10.1021/acsnano.5c18549

Before a promising new therapy can reach a patient, researchers need to answer a deceptively simple question: Will it work? 

And, for some, the rent rises.

Long after a natural disaster fades from the headlines, economic aftershocks can still push people out of their communities, not because their homes were destroyed, but because they can no longer afford to remain there.

A new Georgia Tech-led study found that rents were 6.5% to 12.5% higher than expected four years after a disaster. Similar communities that weren’t hit did not see the same jump.

Brian An, an associate professor in the Jimmy and Rosalynn Carter School of Public Policy within the Ivan Allen College of Liberal Arts, and his team studied two decades of rental housing data and federal disaster records from California and Florida. 

“We often think of housing as a market that will sort itself out,” An said. “But a natural disaster is not a normal market condition. Housing is destroyed. People are displaced. In those moments, renters can become especially vulnerable.”

After a disaster, the housing market’s usual rules no longer apply. Damaged apartment buildings mean reduced supply. Displaced homeowners enter the rental market while their homes are repaired or rebuilt. Construction, repairs, and insurance all get more expensive.

The largest rent increases followed hurricanes and wildfires more than earthquakes, flooding, and tornadoes. For communities hit repeatedly, each new storm or fire added more rent pressure. 

More Demand, Less Room

“When rents go up after a disaster, we're not talking about a small segment of housing,” An said. “We're talking about the broader rental market. That means the effects reach far beyond the homes that were damaged.”

For renters, the consequences extend beyond monthly housing costs. Higher rents can make it harder for families to remain close to support networks. Children may have to change schools. Workers may face longer commutes. Longtime residents can find themselves priced out of communities they helped build.

The findings point to a central tension in disaster recovery: Rebuilding homes is not the same as keeping communities intact.

A Different Path Home

Not every community experienced the same outcome.

Areas that received federal support through Community Development Block Grant Disaster Recovery (CDBG-DR) funds saw smaller rent increases than similar communities that did not. The money can be used to build and preserve affordable rental housing, giving residents more options as their communities recover.

An said the study cannot prove that funding alone caused rents to rise more slowly. But the pattern suggests that recovery resources may shape who can afford to stay in a community once rebuilding begins.

Rebuilding Lives, Not Just Homes

As communities face repeated hurricanes, wildfires, and other disasters, An believes policymakers need to think differently about recovery. That could mean investing in more resilient housing, expanding affordable rental options, and strengthening protections for renters after disasters strike.

“Everyone needs a place to live,” An said. “As disasters become more frequent, housing can't be an afterthought in recovery.”

An’s research is published in The Russell Sage Foundation Journal of the Social Sciences.

In a landmark study published in Nature, 11 researchers tracked the impacts on the carbon cycle across the Mississippi watershed and its 11 states after almost a century of liming. The results show that while liming can initially release carbon, it becomes a carbon sink after a few decades, effectively removing the greenhouse gas from the atmosphere.

“Farmers have been doing enhanced weathering in U.S. agriculture for a little over a half century,” said Chris Reinhard, an associate professor in the School of Earth and Atmospheric Sciences and an author on the paper. “This is a giant natural experiment that's been going on for decades that allows us to figure out how much carbon makes it all the way through the watershed system."

The study grew out of a U.S. Department of Energy Earthshot Initiative grant focused on understanding the role agricultural liming could play in long-term carbon removal.

Tracking Carbon

When limestone or other carbonate minerals are added to soil, the effects don't stop at the field's edge. The minerals’ reaction with the ground’s acidity results in chemical products that move through rivers and eventually reach the ocean. While carbon-related changes can be measured in the field, tracing them across an entire watershed is far more difficult.

But data from decades of agricultural lime applications, fertilizer usage numbers, and river alkalinity measurements at the mouth of the Mississippi helped researchers piece together the larger picture. By analyzing more than a century of agricultural and river records, the team found that liming in the Mississippi River Basin has acted as a net carbon sink.

The findings also challenge how liming's climate impacts are typically measured. Current carbon accounting often treats lime application itself as a source of emissions. But the researchers say this approach misses an important part of the picture: Fertilizers can make soils more acidic over time, creating the need for liming. When the team accounted for both processes, they found that liming removed carbon in the long term, but fertilizer causes acidity and drives emissions. 

Modeling a Better Future

Reinhard and colleagues also created a model that captures the physics and chemistry of agricultural soils. The model can determine liming’s theoretical carbon-removal potential, testing its predictions against the historical data. In this case, about 90% of the carbon-removal benefit predicted from the model ultimately appeared in the records of river chemistry from the Mississippi River Basin. 

“The long-term goal for the model is to develop a way for farmers to plan and be able to answer questions like, ‘How do I stagger the application of lime so I'm helping the crops while also emitting as little carbon as possible?’” Reinhard said.

Beyond its climate implications, liming could help strengthen the long-term resilience of the agricultural industry. The findings suggest that managing soil pH can improve soil health and crop yields, while simultaneously reducing net greenhouse gas emissions. If managed well, one of agriculture's oldest soil management practices may offer a rare double benefit: helping farmers grow healthier crops while reducing the industry's climate footprint.

CITATION : Suhrhoff, T.J., Reinhard, C.T., Kanzaki, Y. et al. Agricultural liming is a carbon sink in the Mississippi River Basin. Nature (2026). https://doi.org/10.1038/s41586-026-11040-2

His paper, “Brain Speaks Louder Than Words: Neurophysiological Opinion Inference via Cognitive Dissonance Triggers,” recently received the 2026 Dr. Hermann Zemlicka Award for the most visionary paper at the NeuroIS Retreat. 

Wu discusses the research, its potential applications, and the ethical and privacy considerations it raises.

Q&A With D.J. 

What was your reaction when you learned your paper received the 2026 Dr. Hermann Zemlicka Award for “most visionary” research?

The Dr. Hermann Zemlicka Award is presented annually at the NeuroIS Retreat to the paper selected as the year’s “most visionary.” I was surprised and deeply honored to receive it. The recognition was especially meaningful because it affirmed our vision of bringing neuroscience and information systems research together to explore a new way of understanding human opinions.

For readers unfamiliar with your research, what problem were you trying to solve?

We wanted to find a better way to understand people’s opinions in situations where traditional methods, like surveys or tracking behavior, may be biased, intrusive, slow, or difficult to use. Our research explores whether brief brain activity measured by electroencephalography (EEG) can reveal when a statement matches or conflicts with a person’s beliefs. If so, it could provide another way to understand opinions without relying only on what people say or how they behave.

Most people are used to answering surveys, reviews, and polls. What made you wonder if there might be a better way to understand what people really think?

Surveys are extremely useful, but they depend on people actively participating. Those answers can be shaped by factors such as memory, the way a question is worded, social pressure, or a person’s ability and willingness to respond. We wondered whether brain activity could offer another way to understand people’s opinions, especially in situations where those challenges come into play. We wanted to see whether we could capture an immediate reaction before a person has to translate it into words.

The paper title, “Brain Speaks Louder Than Words,” is interesting. Can you give an example of what that means in everyday life?

Imagine someone is asked to rate the statement, “I like this product or service.” Even if they feel pressure to give a positive answer, their brain may respond differently depending on whether the statement matches their experience. Our method looks for patterns of brain activity that occur when there is a mismatch between what a person truly believes and what they are evaluating. It is not mind-reading or lie detection. Instead, it uses the brain’s response to conflicting information as one signal that may help us understand whether a statement reflects someone’s genuine opinion.

Were there any findings that surprised you or challenged what you expected going into the project?

One finding was that cognitive conflict depended on more than whether a statement contradicted someone’s opinion. When a heuristic cue, a simple signal that offers a mental shortcut, was present, the brain response to a conflicting statement became weaker. Put intuitively, some contextual cues can soften our immediate sense that “this does not match what I believe,” even when our underlying opinion remains unchanged.

Privacy is a growing concern in today's digital world. Can you compare the privacy implication of the proposed approach versus the traditional methods?

Our approach could reduce the need to store information such as browsing histories, ratings, or written survey responses. Instead of continuously tracking a person’s behavior, it focuses on collecting a specific brain response during a defined interaction with the user’s consent.

At the same time, brain activity is sensitive biometric information and could reveal more than what is needed for a particular task. Any privacy benefits therefore depend on robust safeguards, including data minimization, meaningful informed consent, clearly defined limits on data use and retention, and strong data security through offline, locally controlled processing and calibration.

Our study offers some initial guidance on these issues, but more research is needed to fully understand the privacy implications of this approach.

How could this research change the way organizations understand customers, employees, or other stakeholders in real time?

In situations where surveys may not tell the whole story, receiving feedback is difficult, or past behavioral data are unavailable, our research could eventually help organizations better understand how people are reacting in near real time. For example, it could help identify whether stakeholders' immediate responses suggest agreement or disagreement with a message, product, digital experience, or decision.

These insights would not replace surveys. Instead, they could complement them by showing where people's immediate reactions align with, or differ from, what they later report. Any use at the individual level, however, would require informed consent, a clearly defined purpose, and strong privacy safeguards.

The paper points to opportunities for helping people who may have difficulty communicating through traditional methods. What possibilities do you see for making technology more inclusive?

Brain-computer interfaces have already shown promise in helping people with severe motor or communication impairments interact with technology. Our research explores one possible way to better understand a person's opinions or preferences through brain activity during specific tasks. Over time, this type of work could contribute to technologies that are more responsive to individual needs and more accessible for people who face challenges communicating through traditional methods.

For readers who haven’t thought about neuroscience or brain-computer interfaces before, what’s the one takeaway you hope they remember from this research?

Brain signals do not provide a direct window into a person's thoughts. They reflect many different processes happening in the brain and body, which means they can be difficult to interpret.

That is why theory and experimental design matter. Rather than searching brain data for patterns without a clear explanation, our research focuses on a specific mechanism: how people respond to information that conflicts with their beliefs. By testing that idea in a controlled setting and calibrating the approach for each individual, we can make the results more meaningful and easier to interpret.

Learn More: Information Technology Management

Most people would recognize that something unexpected has happened and adjust accordingly.  

For machines, it’s not always that simple.  

Researchers at Georgia Tech’s H. Milton Stewart School of Industrial and Systems Engineering (ISyE) are addressing this very challenge: how can autonomous systems recognize when something unexpected has happened, determine whether it matters, and decide how to respond?

In a recent paper published in the INFORMS Journal on Data Science, the research team introduced a new framework called Mutual Information Surprise, designed to help machines identify meaningful surprises in complex environments. The work could help lay the foundation for AI agents, robots, and autonomous systems that can better navigate unexpected situations, avoid costly mistakes, and make more informed decisions when faced with situations they weren’t designed or trained to handle.  

"Traditional automation systems are designed to follow instructions. They do not have a sense of surprise. Machines follow a predetermined recipe and produce the expected result," said Yu Ding, the Anderson-Interface Chair and professor in ISyE, who is leading this project. " Intelligent agents, however, must do more than simply follow instructions. They need to recognize when their current understanding or reasoning process has become inadequate. Humans routinely use surprise for this purpose. An autonomous machine needs an analogous computational capability."

This research concept was jointly worked out by Xiao Liu, the David M. McKenney Family Associate Professor, as well as a former postdoctoral fellow in ISyE, Yinsong Wang, and Ph.D. student Quan Zeng.

While several methods already exist to measure surprise in machines, such as the "Shannon Surprise" and "Bayesian Surprise," the ISyE team saw limitations in both approaches.  

Shannon Surprise tends to focus on the rarity of an event, while Bayesian Surprise focuses on how much a new observation changes a system's beliefs.

To illustrate the limitations of existing surprise measures, Ding pointed to the examples of someone noticing a specific type of car parked nearby or a student who consistently earns top grades but suddenly performs poorly on an exam.

Existing surprise measures don't always flag the right kinds of moments to be surprised, Ding said. To the examples given, the Shannon Surprise would flag the specific car parked nearby, although people typically wouldn’t be surprised by that event. Conversely, people would be surprised by the student performing poorly, but the Bayesian Surprise would not flag it.    

"We introduce this new surprise definition because it measures the gain of knowledge and epistemic progression, thus capturing the right moments when a system should be surprised and ignoring the moments when it shouldn't," Ding added.  

The framework could eventually help systems determine when to continue as planned or when to stop and reassess, whether that's an AI assistant struggling to answer a question, a robot encountering a situation it has never seen before, or an autonomous factory detecting a disruption that could affect production and require human intervention.

Looking ahead, the ISyE research team is exploring potential applications in engineering autonomous systems and is developing a proposal for federally funded programs.  

Since its launch in 2025, SRI has brought together researchers from across campus to advance interdisciplinary space initiatives and create new opportunities for collaboration. In their new roles, Ballantyne and Borowitz will help guide the institute's growth by strengthening both internal research connections and external partnerships across the broader space community.

“David and Mariel bring complementary strengths that will be invaluable as we continue building SRI,” said Jud Ready, executive director of SRI. “David has a deep understanding of the research enterprise at Georgia Tech and a passion for connecting people and ideas across disciplines. Mariel brings extensive experience working across government, industry, and the international space community. Together, they will help us strengthen Georgia Tech's space ecosystem and expand our impact far beyond campus.”

Strengthening Georgia Tech's Research Community

Since joining the Institute in 2008 as a founding faculty member of the Center for Relativistic Astrophysics, Ballantyne has helped advance both space science and academic leadership across campus.

A professor in the School of Physics, he studies the evolution of galaxies and their central black holes, as well as the physics of accretion disks around black holes and neutron stars. He has authored more than 140 peer-reviewed publications and served as associate chair of the School of Physics for nearly a decade.

As associate director, Ballantyne will focus on cultivating connections across Georgia Tech's space research community and identifying opportunities for new interdisciplinary collaborations.

“I view SRI as a catalyst — a mechanism to spark new and transformative areas of space research at Georgia Tech that will grow to national and international prominence,” Ballantyne said. “There is so much innovative space research happening across campus, and one of SRI's most important roles is helping researchers find the connections and collaborations that can spark new ideas and discoveries.”

Ballantyne says he is particularly interested in helping position Georgia Tech as a leader in understanding the opportunities and challenges presented by artificial intelligence in space systems.

“My goal is to be out in the community, learning about the breadth of space research happening across campus and identifying ways SRI can accelerate that work,” he said. “AI technologies are poised to transform space exploration, scientific discovery, national security, and commercial space operations. SRI is uniquely positioned to help Georgia Tech lead those conversations.”

Building Partnerships Beyond Campus

As space activities become increasingly interconnected across government, industry, and academia, strong partnerships are essential to translating research into real-world impact. That collaborative spirit is central to the work of Mariel Borowitz, an associate professor in the Sam Nunn School of International Affairs.

Borowitz, who also serves as director of Georgia Tech’s Center for Space Policy and International Relations, is widely recognized for her expertise in space policy, international cooperation, and the governance of emerging space activities. Her work has connected her with space agencies, private companies, and policymakers around the world, providing a valuable perspective on opportunities for Georgia Tech to expand its engagement with the broader space community.

In her role as associate director, Borowitz will focus on growing SRI's partnerships with industry, government, and the broader space community.

“My focus as associate director will be on building partnerships between Georgia Tech and the broader space community,” Borowitz said. “Georgia Tech has tremendous expertise across science, engineering, policy, economics, and international affairs. By working across those disciplines, we can help address the complex challenges facing the future of space development while creating new opportunities for collaboration and impact.”

Borowitz sees SRI as a powerful mechanism for connecting Georgia Tech's diverse strengths and amplifying their collective impact.

“Real-world challenges and opportunities are inherently interdisciplinary,” she said. “The Space Research Institute allows us to bring together expertise from across Georgia Tech to develop more complete solutions and create new possibilities for the future of space.”

Looking Ahead

Together, Ballantyne and Borowitz will help advance SRI's mission of connecting researchers, educators, students, industry leaders, and policymakers to address the most pressing opportunities and challenges in space.

“Space exploration has always challenged us to think bigger, work across boundaries, and pursue questions that no single discipline can answer alone,” said Ready, who also serves as a principal research engineer at the Georgia Tech Research Institute. “David and Mariel embody that spirit of collaboration, and their leadership will help us create new opportunities for discovery, innovation, and impact at Georgia Tech and beyond.”
 

Upon returning to Georgia Tech, Phute reflected on her summer internship and what it taught her about the evolving relationship between research and industry.

Student: Mansi Phute

Research Interests: Machine learning (ML) robustness and artificial intelligence (AI) safety

Degree Program: Ph.D. in Computer Science

Faculty Advisor: School of CSE Professor and Associate Chair Polo Chau

2026 Internship: International Business Machines (IBM), San Jose, California

What about IBM interested you in applying for and accepting an internship there?

IBM is often at the forefront of AI safety, my field of interest, and has a culture that encourages exploratory and fundamental research. I felt this would give me a closer look at cutting-edge industry approaches without compromising on my research interests or my progress toward my thesis.

How well did your coursework and experience at Georgia Tech prepare you for your IBM internship?

My experience at Georgia Tech was very helpful in preparing me for IBM. My coursework and other academic experiences certainly transferred over, but I believe that the wide range of people I met during those courses and what I learned from them helped me connect and relate strongly with people at IBM. Being conversant in different fields of research really helped me interact better with IBM coworkers and feel comfortable in a new environment.

What did you work on while interning at IBM?

I worked on IBM’s AI Foundations team, focusing on the security of multimodal agent communication during my internship. This is an important problem as we see an increase in agents applied in many use cases. It was also closely aligned with my research interests of AI safety.

Do you have a favorite memory or remarkable achievement from your internship?

One of my favorite moments was presenting my work to a broad, cross-team audience of technical and non-technical members. Afterward, my manager told me I was good at explaining my research to people with varying levels of familiarity with the domain. This feedback meant a lot to me because communicating clearly across different audiences is a skill I've deliberately worked to improve. So, hearing that the effort was paying off was very rewarding.

Overall, how helpful was this internship toward your studies at Georgia Tech and your career as an aspiring researcher?

This internship was very valuable for my development as an aspiring researcher. I worked alongside accomplished people in the AI safety field on projects that aligned closely with my research interests. I also saw how those same projects connect to a company's broader business priorities, a perspective that isn’t easily available in academic settings. I shared many fruitful discussions with people working in safety, policy, and alignment, which gave me a much clearer sense of how industry approaches these issues compared to the more academic-oriented framing I am used to.

Based on what you learned during your internship, how important is private industry in progressing research and scientific discovery?

Working in private industry was a fascinating experience. I come away believing that industry plays an important role in advancing research, especially in AI, where companies have access to computing resources that are less prohibitive than in academic environments. I also think that because private industry has a strong hand in implementing and deploying research, understanding industry priorities can help us frame and design our research in ways that complement industry applications. This ensures research has a bigger impact, particularly in the domain of ML safety and reliability.

This summer, M.S. student Joey Cuthbert contributed to this mission through an internship at the Air Force Research Laboratory (AFRL). Upon returning to campus, Cuthbert reflected on his internship and what he learned working alongside researchers in government and the defense community.  

Student: Joey Cuthbert

Research Interests: Machine learning (ML), model-based systems engineering

Degree Program: M.S. in Computational Science and Engineering, home unit in H. Milton Stewart School of Industrial and Systems Engineering

2026 Internship: Sensors Directorate Internship Program with Air Force Research Laboratory (AFRL) and the National Air and Space Intelligence Center (NASIC), Beavercreek, Ohio

What about AFRL interested you in applying for and accepting an internship there?

The Sensors Directorate Internship Program (SDIP) provided a unique opportunity to work alongside mentors from AFRL and NASIC on a defense-related research project over a 14-week internship. This aligned with my desire to work on applied ML research in the defense sector and allowed me to better understand the ins and outs of government and government-contracting work. The program provided competitive pay and housing throughout the program, which was a huge plus for me.

How well did your coursework and experience at Georgia Tech prepare you for your AFRL internship?

My experience and coursework at Georgia Tech helped me a great deal this summer. I believe my understanding of ML has greatly improved over the past two semesters, which helped me complete my internship project. All of my experiments ran on high-performance computing (HPC) systems, and I felt I had a head start since I completed an HPC class last spring. 

What did you work on while interning at AFRL?

I worked on an image-classification robustness project for convolutional neural networks (CNNs) using synthetic aperture radar (SAR) data. I built a robustness benchmark by testing a model against nine types of noise, and used it to show how we can effectively increase robustness by inducing shape-bias in the model during training. 

Do you have a favorite memory or remarkable achievement from your internship?

During the summer, we went on a tour of nearby Wright-Patterson Air Force Base, where we visited the sensors directorate buildings and checked out some of their labs. I also received the best poster presentation award among approximately 40 interns. 

Overall, how helpful was this internship toward your studies at Georgia Tech and career as an aspiring researcher?

This program provided great strides toward my research career goals. My coursework has provided a great foundation in ML, and I was able to apply this knowledge to a project. The internship offered me lots of autonomy, as well as time to explore different paths to find results. 

From what you learned on your internship, how important are government agencies in progressing research and scientific discovery?

I believe government agencies are massively valuable in advancing research and scientific discovery, especially within the defense sector. All work at AFRL has the goal of giving warfighters the greatest advantage possible. This often entails looking 10 to 20 years into the future of science and technology and trying to get there as fast as possible. 

The internship provided Burnett with valuable insight into national laboratory research and reinforced skills he developed through his studies at Georgia Tech. When he returned to campus, we asked Burnett to share more about his internship and what he learned.

Student: Tage Burnett

Research Interests: Fusion energy, computational plasma physics, high-performance computing, and structure-preserving machine learning

Degree Program: Ph.D. in Computational Science and Engineering

Faculty Advisor: School of CSE Assistant Professor Qi Tang

2026 Internship: Oak Ridge National Laboratory, Oak Ridge, Tennessee

Many people are unfamiliar with national laboratories, like ORNL. Could you explain the purpose of these institutions and why they are important?

The Department of Energy (DOE) national laboratories are responsible for moving forward science and technology in the United States and solving high-consequence challenges in science, energy, and national security. They work on both applied and theoretical research with both short-term and long-term returns. ORNL has eight core research areas: biology and environment, energy science, fusion and fission, isotopes, physical sciences, national security, neutron science, and supercomputing. I was an intern in the supercomputing division.

How well did coursework and experience at Georgia Tech prepare you for your ORNL internship?

My coursework at Georgia Tech was vital in my preparation for this internship. I wrote highly parallel code where I leaned heavily on what I learned in CSE 6220: High-Performance Computing. I also worked on numerical methods which required an understanding of partial differential equations and numerical linear algebra which I also learned at Georgia Tech from classes like CSE 6643: Numerical Linear Algebra and a space plasma physics course.

What did you work on while interning at ORNL?

At ORNL, I was a developer on the Adaptive Sparse Grid Discretization (ASGarD) codebase. The code uses adaptive sparse grids and the Discontinuous Galerkin method to beat the curse of dimensionality and solve high-dimensional partial differential equations (PDEs). The code is designed to simulate fully kinetic plasmas in up to 6-dimensional phase space. My project was to implement an iterative method to solve the efficiently solve the Poisson equation within the codebase. This project gave me hands on experience with linear algebra, numerical PDEs, parallel computing and software engineering which was invaluable to my development as a CSE researcher.

Do you have a favorite memory or remarkable achievement from your internship?

My favorite memory from my internship was spending time with the other ORNL interns outside of work. There was an amazing group of interns at ORNL, and it was great getting to know them. One particularly good memory was when we went out to a restaurant with live music and played laser tag during our last week of the internship to celebrate our time at ORNL. The achievement I am most proud of was getting a working, highly efficient version of the Poisson solver into ASGarD. The ASGarD codebase is open source, so I hope other plasma physics researchers will use the code and find it helpful for their research.

While interning, you were selected for a GEM Fellowship, which Georgia Tech and ORNL nominated you for. What does this fellowship mean to you and is there anything you would like to say to your supporters?

To me, receiving the GEM Fellowship indicates that other people recognize the hard work I am doing, and they believe in my ability to meaningfully contribute to the field. Having this support from GEM, ORNL, and Georgia Tech gives me greater confidence in myself and my potential and inspires me to put my all into my work. I would like all my supporters to know that I am so grateful for the opportunity you have given me to be a part of the excellent community of researchers within GEM, ORNL, and Georgia Tech. I will do my very best to make your support worthwhile!

Overall, how helpful was this internship toward your studies at Georgia Tech and career as an aspiring researcher?

The internship was extremely important to both my studies at Georgia Tech and my career as a researcher. The hands-on experience I gained is irreplaceable and it helped me to apply all the skills I have developed throughout my education. I am also optimistic that the internship will open doors for me when I am seeking a job post-graduation.

Ahmadi and Brown find that neighborhoods with higher shares of Black residents experience higher energy burdens, even after accounting for factors such as income, renter status, and housing characteristics. In this study, energy burden refers mainly to the share of household income spent on electricity, gas, and water. The authors estimate that an approximately 11 percentage-point increase in a neighborhood’s Black population share is associated with about a 1 percentage-point increase in household energy burden, equal to an average annual increase of about $785 in utility costs. These findings suggest that unequal energy burdens are tied not only to household finances, but also to the lasting effects of segregation and discrimination. 

Read Full Story on the EPIcenter Page

When Chevron reported its highest quarterly profit in six years on July 31, 2026, it was just one detail in a larger picture: Analyst firm Wood Mackenzie estimates the global oil and gas industry is on course for a cash windfall of US$495 billion in 2026. That’s profit above and beyond what the industry expected before the U.S.-Israel war with Iran began.

Three separate bills seeking to tax those profits are now in Congress, and President Donald Trump has even said the oil companies are “making too much money.”

As an applied microeconomist, I am often asked how taxes affect economic activity. Economists have long held a more nuanced view of windfall taxes than either side of the current debate suggests. Advocates often make overly optimistic revenue projections, and opponents often overstate how much such a tax might discourage investment. A 1980s U.S. windfall-tax experiment is instructive on both counts.

Read Full Story on The Conversation

The GTRI field office, which includes a new large secure classified workspace, will house GTRI engineers and scientists working shoulder to shoulder with U.S. Space Force teams. The Colorado Springs Field Office currently has forty GTRI personnel on staff.  The arrangement reflects a growing conviction inside the defense community that the pace of modern threats requires a closer, faster collaboration between researchers and the warfighters they support. 
 

“We won’t have to go through layers of translation because the government people with technology needs will be sitting next to the GTRI engineers offering solutions. It makes for a very close interaction that we expect to continue for many years to come” said John Bunnell, GTRI’s Director of Space Program Development.

Read the entire article on the GTRI News page

Despite decades of research, the chaotic nature of turbulence makes it difficult to predict and control. This challenge impedes more than smoother air travel. Solving the turbulence problem could lead to advances in areas ranging from sustainable energy to training a smarter workforce for the era of artificial intelligence (AI).

To advance understanding of turbulence, the National Science Foundation is establishing a new, $30 million Science and Technology Center (STC) at Michigan State University. Georgia Tech is among eight universities supporting the center.

Assistant Professor Qi Tang will join the STC for Transformative Explorations in Multi-Physics and Engineering of Scientific Turbulence (TEMPEST). TEMPEST, launching on Sept. 1, aims to build trustworthy, predictive models of real-world turbulence. 

Tang will lead TEMPEST’s modeling and scientific machine learning (ML) efforts. NSF will fund Tang and Georgia Tech with over $1 million from the center’s five-year, $30 million award.

By understanding and predicting turbulence, TEMPEST can unlock new applications, with a focus on fusion energy and national security. The center will also generate long-term research projects with applications in air and space flight, manufacturing, chemistry, and broaden science education and AI fluency.

“Turbulence has resisted prediction for a century,” said Tang, a faculty member in the School of Computational Science and Engineering (CSE).

“STC TEMPEST aims to develop a unified, predictive science that advances fusion energy, improves hypersonic technologies, and deepens our understanding of how stars created the elements that make up our world and ourselves. For everyday people, the center points toward abundant clean energy and faster, more efficient flight."

Turbulence is the motion of a fluid characterized by chaotic changes in pressure and speed. Turbulent flows can occur across all scales, from interactions between subatomic particles to astrophysical scales, including supernovas, black holes, and cosmic rays. 

While turbulent flows are common and occur naturally, scientists still do not fully understand them. Small changes in a turbulent flow can produce dramatically different outcomes. Combined with the countless interactions across multiple scales of time and space, this makes turbulence extraordinarily difficult to predict.

“Rather than studying individual pieces of this enormously complex problem in isolation, we are bringing together theory, experimentation, computation and artificial intelligence to develop a deeper understanding of turbulence across scales,” said Michael Murillo, an MSU professor and the director of TEMPEST. 

“Our goal is not simply to understand turbulence better, but to make it predictable and controllable in ways that will enable new technologies and scientific discoveries.”

The NSF TEMPEST award supports students and researchers at Michigan State University, Auburn University, Baylor University, Georgia Tech, San José State University, Texas A&M University-Corpus Christi, University of Rochester, and Yale University to combine theory, computation, AI techniques, and experimentation to build trustworthy predictive models of real-world turbulence for high-consequence applications.

Additional partners include Los Alamos National Laboratory, Sandia National Laboratories, Lawrence Livermore National Laboratory, Pacific Fusion, and General Atomics.

Together, TEMPEST researchers will build more accurate and reliable physics-grounded models. The center will test new ideas against real-world observations, then use those results to refine the models. 

Tang contributes expertise in ML, scientific computing, and plasma physics to STC TEMPEST. 

Earlier this year, Tang received an Early Career Research award from the Department of Energy’s Office of Science. He is using the award to build ML and data science tools that help scientists analyze massive datasets from fusion experiments and simulations.

This interdisciplinary approach is intended to move science from understanding why turbulence behaves as it does to predicting how it will behave. Through prediction and simulation, scientists could eventually engineer solutions to control turbulence in real-world scenarios.

The center will make its data and software broadly available and engage the public through museum exhibitions, immersive media, and educational programs that are expected to reach more than 10,000 K-12 students annually. TEMPEST will also help train an AI-fluent scientific workforce prepared to tackle complex problems across disciplines.

“One reason I am excited to work in TEMPEST is because it aligns perfectly with our School of CSE mission. As a discipline, CSE complements theory and experimentation as a mode of scientific discovery,” Tang said. 

“We build computational models to simulate scientific and engineering concepts, like turbulence in this case, so that we can test theories that are too difficult, expensive, or risky for physical experiments.”

But recent research from Georgia Tech’s School of Economics in the Ivan Allen College of Liberal Arts suggests adding an asterisk to earlier research that makes that conclusion, saying previous studies failed to account for one simple fact: people adapt. 

Georgia Tech economist Bobby Harris used a massive database of Fitbit step count data to measure how temperature shapes physical activity and found that extreme heat cuts step counts by 6% when compared to ideal weather. And while residents of the warmest regions cut their activity by an average of only 354 steps on days over 100 degrees, those living in the coldest regions cut theirs by 1,081, according to Harris’ analysis. 

To be fair, cold bites, too. On days that stay below freezing, people take roughly 1,000 fewer steps. That’s a 12% drop, enough to pack on a pound over the course of a typical Madison, Wisconsin winter, Harris found. 

But as the climate grows warmer, how humanity will respond to warmer temperatures remains a significant concern. In fact, earlier research projected that, by 2050, temperature-driven declines in physical activity could contribute to 500,000 premature deaths a year worldwide and annual productivity losses topping $2.4 billion. 

Projections like those typically assume everyone responds to heat the same way, with no capacity to adapt, Harris said.  

Read Full Story on the IAC News Page
 

Deciding which candidates deserve scarce laboratory time is itself a hard problem. It requires weighing scientific plausibility against practical constraints — likely impact, expected effectiveness, and eventual manufacturability — considerations that are difficult to apply consistently across thousands of candidates.
 

An artificial intelligence (AI) program developed at the Georgia Tech Research Institute (GTRI) could provide a new way to narrow that hypothesis pool down to a rate that robotic laboratories can actually test, and more broadly, to evaluate a wide range of scientific and technical claims that would otherwise overwhelm human assessment.
 

Known as FARSCAPE, the program was developed to support a research project organized by the U.S. Defense Advanced Research Projects Agency (DARPA) to evaluate a broad range of feasibility questions. By breaking down challenging questions into smaller components that can be evaluated by a team of independent computer agents, FARSCAPE uses a “chain of thought” approach to provide answers in the form of probabilities. It then helps humans check the rationales for its assessment.
 

Read the full article on the Georgia Tech Research Institute news page

Georgia Tech researchers spent two years helping to answer that question through DARPA’s AI Cyber Challenge (AIxCC), a competition designed to test whether AI could identify and fix security vulnerabilities in real-world software.

Now, they are sharing what they learned with the cybersecurity community.

Their paper, SoK: DARPA’s AI Cyber Challenge (AIxCC): Competition Design, Architectures, and Lessons Learned, was presented at USENIX Security 2026, one of the world's leading cybersecurity conferences. The paper was selected as a runner-up for the conference’s distinguished paper award, placing it among 36 recognized papers from 362 accepted papers out of 3,028 submissions.

The paper examines how the seven finalist teams approached the competition and what the results reveal about the future of AI-powered cybersecurity.

Putting AI to the Test

AIxCC challenged teams to build Cyber Reasoning Systems (CRSs) that could operate with minimal human assistance to identify software vulnerabilities, develop fixes, and determine whether security alerts were real threats.

The teams had 143 hours to analyze 53 software projects during the final competition.

Georgia Tech’s Team Atlanta, which won the competition, used an approach that combined multiple AI agents with traditional security tools. Other teams used different approaches, including applying AI for specific tasks or building highly autonomous AI agents.

The variety of systems provided researchers with a rare opportunity to compare different approaches to AI-powered cybersecurity.

Lesson from the Competition

One of the biggest lessons was that reliability matters as much as intelligence.

Some systems were highly capable but struggled to remain operational while analyzing large, complicated software projects. The strongest systems were often those that could work reliably throughout the competition.

The researchers also found that AI and traditional security tools have different strengths. Traditional tools were still effective at finding common bugs, while AI performed better at reasoning through more complex problems.

However, AI-generated fixes remain a major challenge.

Researchers found that 38% to 46% of AI-generated patches were semantically incorrect. This means a patch might stop a security problem but also break a feature or create another problem.

The results show that AI can play an important role in cybersecurity, but human experts are still needed to verify the safety of AI-generated fixes.

Sharing the Lessons

Cen Zhang, the paper’s first author, said the research offers a unique look at the competition by combining lessons from the finalist teams, organizers, and DARPA’s data.

“This paper provides a unique angle on how AIxCC was designed, the techniques teams used, and what the scores reveal and conceal,” Zhang said.

Jiho Kim presented the paper at USENIX Security 2026. He said the presentation was an opportunity to share lessons from two years of work with the broader cybersecurity community.

“Seeing the strong interest and thoughtful questions from the audience made the experience particularly rewarding,” Kim said.

The researchers say they hope the lessons from AIxCC will help guide the next generation of cybersecurity tools.

The committee, convened through the National Academies' project Future of Battery Technology Options for Defense Applications, will identify the strengths and weaknesses of future battery technologies, including an examination of performance, safety, and manufacturability across technology and manufacturing readiness levels. The committee will also identify gaps where research investments could potentially improve battery capabilities across technology and manufacturing readiness levels, creating opportunities to leverage commercially available technologies.

With a joint appointment in MSE and the George W. Woodruff School of Mechanical Engineering, McDowell is internationally recognized for his research on batteries and energy storage materials. His work focuses on understanding how materials change during battery operation and using that knowledge to develop safer, more efficient, and more sustainable energy storage systems. McDowell is also co-director of the Georgia Tech Advanced Battery Center. He leads research spanning solid-state batteries, lithium-ion and sodium-ion technologies, and next-generation energy storage materials. “I am very thankful to be selected, and I look forward to working with colleagues on developing recommendations to advance battery technologies in support of our country," said McDowell.

Read Full Story on the MSE Newspage

This award is part of NASA’s Space Technology Research Grants Program, which supports groundbreaking projects with the potential to transform space science and technology.

Through the three-year, $750,000 award, Mazumdar and her research team will develop laser-based methods to simultaneously measure temperature, chemical species, gas velocity, and other properties in the gases surrounding heat shield materials.

“We aim to implement our measurement techniques in arc jet or plasma jet facilities, like the ones at NASA, to assist with the evaluation of thermal protection systems for next-generation spacecraft,” Mazumdar said.

The project uses ultrafast lasers, which produce extremely short, high-intensity pulses. These pulses allow researchers to study the behavior of molecules on extremely short timescales and measure properties that can improve understanding of the gases surrounding a spacecraft during atmospheric entry.

Mazumdar said she and her students are excited about this project and hope it will help NASA develop new heat shields for spacecraft traveling to destinations such as Mars, Venus, and Titan.

Read Full Story on the ME Webpage

Read more.

A new study led by Francesca Storici, a professor in the School of Biological Sciences and faculty member of the Parker H. Petit Institute for Bioengineering and Bioscience, has uncovered an unexpected feature of human DNA linked to gene activity and the physical organization of DNA. The findings, published in Cell, could change how scientists think about DNA organization, transcription, and genome function. 

Georgia Tech is hosting the 2026 MFEM (Modular Finite Element Methods) Community Workshop, Sept. 22-25. MFEM supports research in computational physics, earth systems modeling, engineering, energy, and other fields. 

The four-day workshop is being held at the Georgia Tech Global Learning Center and will focus on improving software for scientific computing and discovery. Participants can also attend online. Registration for the workshop is open through Sept. 11. 

“We're very excited and grateful for the opportunity to have this workshop at Georgia Tech,” said Tzanio Kolev, a computational mathematician at Lawrence Livermore National Laboratory (LLNL).

“Georgia Tech has a great reputation in our field, and hosting at universities is a great way to connect with students. We see students as our future colleagues who will improve MFEM for generations to come.”

MFEM is an open-source software library for solving equations in computational models. Scientists and engineers use it to build and test virtual designs on some of the world’s most powerful supercomputers before creating real-world prototypes.

In fact, MFEM powered a tsunami early-warning model that ran on El Capitan, the world’s second-fastest supercomputer. The framework completed a simulation in a fraction of a second, 10 billion times faster than conventional algorithms. Kolev was part of the team that won the 2025 Gordon Bell Prize for the project.

MFEM’s impact extends beyond its original developers. The AWS Center for Quantum Computing uses the software as the foundation for a tool called Palace. This project runs 3D electromagnetic simulations to aid in the design of quantum computing hardware.

“These workshops have been very beneficial for both the broader user community and also for MFEM developers,” said Kolev.

“Every workshop, we are surprised by the ways people are building on our work, seeing what incredible, interesting, amazing things they do with it.”

Next month’s workshop at Georgia Tech will connect MFEM users and developers from national laboratories, academia, government, and industry. 

The United Kingdom Atomic Energy Authority joins LLNL and Georgia Tech in sponsoring this year’s workshop. Nearly 20 scientists from Department of Energy (DOE) laboratories are attending in person. They represent LLNL, Los Alamos National Laboratory, Princeton Plasma Physics Laboratory, and the Naval Nuclear Laboratory.

The workshop’s first day features a free, hybrid tutorial. LLNL’s High Performance Computing Innovation Center will lead the tutorial, helping new users get started with MFEM and learn what the software can do. The tutorial requires separate registration for virtual participants.

The workshop will also host a simulation and visualization contest. Participants can submit images and videos of simulations using MFEM, which will be posted in a gallery. The workshop organizers will select an overall winner.

Further workshop activities include:

• MFEM news and roadmap for future projects
• Talks from application developers
• Student-user lightning talks
• In-person poster sessions
• Office hours with MFEM experts

The MFEM workshop highlights the role open-source software plays in scientific discovery. 

By making tools freely available, researchers can build on each other’s work rather than starting from scratch. This shared approach can accelerate innovation, improve software, and make advanced computing tools accessible to a wider community.

Georgia Tech hosts a Center for Scientific Software Engineering and an Open-Source Program Office. This year’s workshop connects these units with the MFEM community to help put the software into the hands of more researchers across science and engineering.

“The MFEM workshop aims to foster collaboration among all MFEM users and developers,” said Qi Tang, a workshop organizer and assistant professor in the School of Computational Science and Engineering.

“Hosting its annual community workshop brings researchers from DOE laboratories, universities, and industry to campus, giving Georgia Tech faculty and students direct access to experts from the field.”

The milestone was driven by startup activity in CREATE-X and Quadrant-i, two cornerstone initiatives of the Office of Commercialization, and reflects the expanding reach of Tech's innovation ecosystem. The programs support students, faculty, researchers, and alumni in transforming ideas into companies within industries ranging from healthcare and robotics to legal technology and accessibility.

"Crossing the 200 startup teams milestone is more than a record. It's a reflection of a commercialization ecosystem that is helping translate ideas into products and companies that solve real problems," said Raghupathy "Siva" Sivakumar, chief commercialization officer. "Building a dense, connected community of founders is essential to our vision of becoming the nation's leading startup campus and maximizing the value of Georgia Tech innovation."

Diverse Paths to Entrepreneurship

The founders behind this year's milestone represent the many paths entrepreneurs can take at Georgia Tech. They come from different disciplines, pursue various industries, and arrive with a wide range of experiences, but all share a desire to solve meaningful problems.

For alumnus Alberto Flores Guerrero, who earned an M.S. in cybersecurity from the Ivan Allen College of Liberal Arts in 2025, and his longtime friend and co-founder, Luis Estala, that journey to CREATE-X began nearly 2,000 miles from Atlanta.

The pair are building Separate, an AI-powered platform designed to help people navigate divorce by simplifying legal processes, organizing paperwork, and connecting users with resources. Drawing on Flores Guerrero's background as a lawyer, the company aims to make one of life's most stressful experiences more manageable.

When they learned about CREATE-X Startup Launch's kickoff just two weeks before it began, they didn't hesitate. Flying wasn't an option, so they packed the car and drove from Mexico to Atlanta.

Four days later, they arrived at Georgia Tech, convinced the opportunity was worth every mile. Inspired by the kickoff experience, Flores Guerrero soon returned to Mexico, packed his belongings, and moved to Atlanta for the summer.

For both of them, Startup Launch became more than a summer program. It gave them the confidence to build their company as part of a community of founders.

"This experience has completely changed the way we think about ourselves and what's possible for our company," Estala said. "This is the chance of our lives."

"I've learned so much just by being around these people," Flores Guerrero said. "Georgia Tech has some of the smartest students in the world, and then you put the most entrepreneurial of them together in one room. Nice things should happen."

Building a Deep-Tech Startup

For Georgia Tech master's student Rohit Gore in the College of Computing and co-founder Patrick Walsh, entrepreneurship began with one idea. But their startup took shape after they pivoted in a new direction.

As they developed a low-cost drone, they kept encountering the same challenge: Robots that performed well in simulations often struggled in real-world environments. After talking with robotics teams across the country, they launched Brio Robotics, a company developing a simulation and automated testing platform for autonomous systems.

CREATE-X Startup Launch helped the team refine its approach to customer discovery, sales, and commercialization.

"We're engineers by trade, and we don't know anything about B2B sales," Gore said, noting that Startup Launch Director Margaret Weniger “has been hugely helpful. It was so valuable to hear her perspective on what good sales metrics look like, what the goal of a customer call should be, and how to approach those conversations."

Today, Brio Robotics is finalizing its first design partnership with a drone company and has five additional robotics companies in its sales pipeline.

Turning Research Into a Startup

While many startups begin with student entrepreneurs, others emerge directly from Georgia Tech's research labs.

For Yue Chen, associate professor in the Wallace H. Coulter Department of Biomedical Engineering, commercialization meant looking beyond the lab. Working with Ph.D. students Yixuan Xia, Yilin Cai, and Samuel Wilcox, Chen launched Fructus, a startup developing robotic harvesting technology to help growers address labor shortages and improve harvesting quality.

The technology began as a USDA-funded blackberry harvesting project. But through Quadrant-i Startup Launch, conversations with growers and industry stakeholders revealed a greater opportunity in Georgia's blueberry industry, prompting the team to pivot toward a larger market and a more pressing need.

"For faculty, we focus on research and developing fundamental science" Chen said. "But there's a gap between the work we do in the lab and the final product." Startup Launch helped bridge that gap through customer discovery. It “gave us the opportunity to get out of the lab, talk to stakeholders, and understand what they really need."  

For Cai, the experience changed the team's perspective. "As researchers, we usually focus on solving a research problem," he said. "Through Startup Launch, we learned to see the problem from the customer's perspective and think about what it really takes to build a product."

Looking Ahead

More than 150 startups will showcase their ventures at CREATE-X Demo Day on Thursday, Sept. 3, at LOOP, Georgia Tech's newest creative arts and performance venue. The event will bring together students, investors, mentors, industry leaders, and the broader community to meet the founders behind this record-breaking cohort and explore the next generation of Georgia Tech innovation.

"This experience has completely changed the way we think about ourselves and what's possible," Estala said. "If you have an idea, just do it. You never know where it might take you.” 

The effort will be coordinated through Georgia Tech's Institute for Matter and Systems (IMS), which will serve as the hub for the Institute’s NNME activities. Drawing on Georgia Tech’s research expertise, educational programs, industry partnerships, and shared facilities, IMS will help strengthen the state’s role in the nation's growing microelectronics ecosystem.

Georgia Tech is part of NNME South, a regional node led by The University of Texas at Austin. The consortium brings together higher education institutions, industry collaborators, workforce organizations, and economic development agencies across 10 states to align education and training with industry needs, expand workforce development opportunities, and create clearer pathways into semiconductor careers. 

"Microelectronics are in everything from consumer technologies to national security," said Mikkel Thomas, associate director for education and outreach at IMS. "Through NNME, we have an opportunity to work alongside industry and academic partners to help teach the next generation of the semiconductor workforce."

This initiative comes as demand for domestic semiconductor talent continues to grow. NNME South projects that approximately 29,000 semiconductor-related positions will be added across the region over the next decade, increasing the need for skilled technicians, engineers, and advanced manufacturing professionals.

IMS brings expertise in advanced materials and substrate innovation to support workforce needs across the semiconductor ecosystem. As part of this effort, IMS will help align educational programs with industry-defined knowledge, skills, and abilities, creating clearer pathways from technical training and certificate programs to advanced degrees and careers.

Through NNME, IMS and its regional partners will work to modernize curricula, expand hands-on learning opportunities, strengthen workforce partnerships, and increase awareness of careers in microelectronics and semiconductor manufacturing. These efforts aim to equip students, educators, and employers with the resources and pathways needed to support the future growth of the U.S. semiconductor industry.

Now, as Professor Edmond Chow prepares to teach at Georgia Tech-Europe for the 2026-2027 academic year, Professor Polo Chau is stepping into the role of associate chair to help guide the School’s next phase of growth. 

Their leadership transition comes at a time when demand for expertise in artificial intelligence (AI), data science and analytics, and high-performance computing accelerates across industry, government, and academia.

“On behalf of the students, faculty, and staff of CSE, I extend our heartfelt gratitude to Edmond for his years of dedicated service as associate chair,” said School of CSE Regents’ Professor and Chair Haesun Park.

“Polo is a respected leader, an accomplished scholar, and a passionate advocate for our community. I am confident he will build on Edmond’s strong foundation to guide the School's continued success.”

The School of CSE associate chair helps lead faculty development, academic planning, and new initiatives. These responsibilities include course scheduling, teaching assignments, and reviewing proposals for new courses.

Rapid growth defined Chow’s tenure as associate chair, which started in summer 2021. 

As associate chair, Chow led CSE’s faculty recruiting committee. The School hired 15 new professors during his term, doubling the faculty in that span.

Chow’s relationship with new hires didn’t end with recruiting. Each new professor needed support to onboard smoothly, which he helped facilitate by pairing new hires with faculty mentors in the School. 

Chow helped new and veteran faculty alike design courses centered on their expertise and the field's emerging needs. As a result, he broadened and enriched the CSE curriculum at Georgia Tech. 

Chow led CSE’s effort to secure space in the Coda Building to accommodate so many new faculty and students. With his help, the School added the east wing of the 13th floor and space for four labs on the fifth floor.

While at Georgia Tech-Europe, Chow will teach CS 7545: Machine Learning Theory and CS 1371: Computing for Engineers. 

Chow is a fellow of the Society for Industrial and Applied Mathematics (SIAM). Like CSE, the professional society recognized Chow’s leadership and administrative talents, selecting him for several roles.

With his associate chair responsibilities concluded, Chow will focus more on his role as SIAM’s vice president for programs. He also co-chairs the organizing committee for the SIAM Conference on CSE, to be held Feb. 22-26, 2027, in Pittsburgh.

Previously, Chow served as vice chair of the SIAM Activity Group on CSE from 2025 to 2026. He co-chaired the organizing committee for SIAM’s 2022 annual meeting. 

"It has been an honor to serve CSE,” Chow said. “I am also inspired to have worked alongside others, including Haesun, who care so much for the School.”

Since joining Georgia Tech in 2012, Chau has distinguished himself as a leading expert in data science and AI.

Chau’s research combines machine learning and visualization to create scalable, interactive tools. His lab has developed applications for studying massive datasets, interpreting complex AI models, and solving real-world problems in cybersecurity, human-centered AI, graph visualization and mining, and social good.

Chau has taught CSE 4242/6242: Data and Visual Analytics since 2013. The course has grown into the world's largest semester-long university class on the subject. More than 19,600 students have taken the course throughout its history.

Alongside his research and teaching, Chau has held several leadership roles at Georgia Tech.

Since 2014, Chau has served as associate director of Georgia Tech’s M.S. Analytics program. The program celebrated its 10th anniversary in 2024, when he received the Innovator Award for his leadership and pioneering approaches to analytics education.

In 2019, Chau accepted roles as director of industry relations for the Institute for Data Engineering and Science (IDEaS) and as associate director of corporate relations for the Machine Learning Center (ML@GT). Chau recently stepped down from his leadership positions with IDEaS and ML@GT to accommodate his responsibilities as CSE’s associate chair.

“I enjoy building deep connections with people, and this role provides a lot of opportunities to do that,” Chau said. “Faculty development helps my colleagues build the careers that they want, and collectively shape CSE’s future. That’s what I look forward to the most.”

Georgia Tech’s Itamar Kolvin is aiming to solve that problem using molecular motors powered by tiny chemical reactions, giving researchers a new way to guide how fibers assemble into larger structures in the lab. The work could open the door to advances in wound healing, artificial tissues, and organ repair.

Now, Kolvin, an assistant professor in the School of Physics, has been awarded a $747,000 CAREER grant from the National Science Foundation (NSF) to support this research.

The NSF Faculty Early Career Development Program is a five-year grant designed to help promising researchers establish a foundation for a lifetime of leadership in their field. Known as CAREER awards, the grants are NSF’s most prestigious funding for early-career faculty.

“The CAREER award is a crucial opportunity to push this research forward,” says Kolvin. “NSF plays a critical role in advancing science, and we wouldn’t be able to do our work without their support. I’m incredibly grateful for their commitment to advancing science.”

Microscopic Motorboats

While the body naturally assembles these fibers, their small size makes protein filaments difficult to control in a lab setting. Without guidance, the materials grow randomly, creating weak and disorganized structures. But Kolvin has found that exposing the filaments to controlled fluid flows can help them grow in predictable ways.

That’s where Kolvin’s molecular motors come in. He attaches the motors to rod-shaped particles called microtubules, transforming the otherwise inert particles into microscopic motorboats. Powered by chemical reactions, the microtubules move through the fluid and generate tiny currents. Those currents guide the suspended protein filaments, directing how they align and assemble.

Like sticks in a stream, the current helps the protein filaments align with the flow around them. When millions of filaments interact in this way, they can form bundles, clusters, and large-scale networks. 

“How do these rods align, when do they tangle, and when do they form networks?” Kolvin asks. “I’m interested in learning how we may be able to predict and ultimately control that behavior in order to direct the ways these structures can grow.”

Flexible Filaments

Kolvin’s earlier work has already shown success with actin, the filaments responsible for building muscles. When suspended in fluid, the molecular motors helped actin fibers bundle together and form a membrane-like structure. 

While that work demonstrated that molecular motors could influence assembly, Kolvin now aims to create a more dynamic, tunable system. Actin is limited, he explains, because of its simple rod-like shape, lack of rigidity, and because its bonds become permanent once the fibers bundle together.

He believes the more rigid, helix-shaped flagella in this new work will offer a wider range of opportunities. “The shape and rigidity of flagella expand the variety of patterns they can form,” he explains. “These new structures could have different applications.”

Toward Tunable Materials

Through molecular engineering, the Kolvin Lab creates flagella that are temperature-sensitive, meaning that they can make and unmake bonds at different temperatures. This property might be key in creating a system that could be assembled and disassembled on demand.

“This could make it possible to tune materials in real-time by warming or cooling the system," Kolvin explains.

By combining molecular motors with temperature-sensitive protein fibers, Kolvin aims to create systems that can be predictably shaped, assembled, and disassembled on demand, opening the door to new possibilities for tissue engineering and regenerative medicine. 

The work could also help answer long-standing problems in physics about active matter and collective behavior, revealing how flow and shape influence the way millions of microscopic building blocks align, pack, and assemble into complex materials.

“This CAREER award provides an exciting opportunity to pursue new ideas and tackle difficult, far-reaching questions,” Kolvin says. “I’m looking forward to seeing where this research leads in the years ahead.”

On Sept. 3, CREATE-X Demo Day will take place for the first time at LOOP, Georgia Tech’s new creative and cultural hub, where more than 100 startups will give a firsthand look at what Tech founders have spent the summer building and launching.