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

The internship provided Burnett 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.

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 machine learning Ph.D. student 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. 

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.

Read more »

The cells that keep vaccines working for decades have long remained a mystery deep within human bone marrow. A new study watched them move, settle, and survive in a living human tissue model, revealing a surprisingly dynamic world that could reshape how scientists think about immunity, aging, cancer, and vaccine protection. 

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. 

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.”

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.

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. 

Previously known as Velocity Startups, The Venture Arcade serves as a bridge between early-stage startup founders who have participated in Georgia Tech initiatives like CREATE-X, Quadrant-i, and Biolocity and are focused on scaling their businesses and preparing themselves for late-stage accelerators such as the Advanced Technology Development Center, Engage, Fusen, and Atlanta Tech Village. 

Hodgson brings more than two decades of entrepreneurial leadership, capital markets expertise, and global operating experience to the role. As CEO of RoxWrite, she led the development of an industry-leading, AI-powered underwriting, onboarding, and risk-monitoring platform. Hodgson co-founded and led Now Corp from 2010 to 2024, serving as president and CEO of the innovative business-to-business payments company that created NowAccount. Earlier in her career, she co-founded Nourish Inc., served as executive VP of Dunk.net and chief marketing officer and chief operating officer of Dewberry Capital Corporation, and was senior vice president and general manager at iXL, where she built and led the Retail and Consumer Products Practice across 26 global offices serving clients such as The Home Depot, Coca-Cola, and Nike. 

"As a Georgia Tech graduate, serial entrepreneur, and longtime mentor to founders at CREATE-X and Harvard Business School, I've seen what it takes to start and scale a business, and I've seen how much faster and more successful that journey can be with the right resources,” she said. “The Venture Arcade is built to deliver exactly that, with access to Georgia Tech’s unparalleled resources. Bringing capital, capacity, and customers, The Venture Arcade’s flywheel of growth will give Georgia Tech founders and local technology companies, including hard tech and deep tech, an unfair advantage. I'm proud to work with Georgia Tech to bring this program to Atlanta, a city ready to take its place as a top five technology and startup hub in the U.S."

Hodgson is also a nationally recognized thought leader on entrepreneurship and access to capital. She co-authored the award-winning book Level Up: Rise Above the Hidden Forces Holding Your Business Back (2022), published by Portfolio Penguin and now widely used in university entrepreneurship courses. She previously served as an entrepreneur-in-residence at Harvard Business School, where she continues to mentor founders and judge venture competitions. She has also served as a mentor in Georgia Tech’s CREATE-X 10x program, coaching high-potential founders as they scale and pursue significant market opportunities.

“Lara possesses the capital formation expertise and business acumen to put The Venture Arcade on the map,” said Raghupathy “Siva” Sivakumar, chief commercialization officer at Georgia Tech and president of Georgia Advanced Technology Ventures. “Her experience building, scaling, and financing companies makes her uniquely suited to shape The Venture Arcade into a meaningful pathway for high-potential startups. Lara truly embodies the entrepreneurial spirit of Georgia Tech, and we are thrilled to have her on the leadership team.” 

A proud Georgia Tech alumna, Hodgson earned her bachelor’s degree in aerospace engineering with highest honors and an MBA from Harvard Business School. She is a trustee of the Georgia Tech Foundation and serves on multiple corporate and nonprofit boards. Her honors include recognition as a 2019 EY Entrepreneurial Winning Woman, a Worthy 100 honoree by Worth magazine, and inclusion in Pathway of Progress, the campus installation celebrating women at Georgia Tech.

About The Venture Arcade

The Venture Arcade is a startup accelerator that propels deep-tech innovation, providing the resources and infrastructure for founders to take their innovations to market. Located in the heart of Tech Square in the historic Biltmore Innovation Center, The Venture Arcade offers mentorship, infrastructure, strategic programming, and funding opportunities. The accelerator is made possible through a partnership with Georgia Advanced Technology Ventures Inc. and the Georgia Tech Foundation. 

Read more »

Through a Next Gen STEM (NGS) NASA Aerospace Skilled Technical Workforce Hubs (NAS_Hub) grant award, Georgia Tech will play a central role in addressing a critical labor shortage in the booming aerospace industry and enhance the state’s role as an aerospace industry leader in the global space economy.

Beginning this fall, the three-year, $1.5 million award will establish the Southeast Space Technology & Aerospace Readiness Skills (SE-STARS) Hub. The hub will expand opportunities for training and workforce readiness in high-demand technical careers in aerospace.
The SE-STARS Hub includes the Georgia Space Grant Consortium (GSGC), Georgia Tech’s Space Research Institute (SRI), the Georgia Tech Manufacturing Institute (GTMI), the Technical College System of Georgia (TCSG), Georgia Southern University, Georgia College and Career Academies, Georgia Aerospace & Defense Alliance (GADA), and select Georgia aerospace employers to support the growing aerospace industry and NASA missions.

Aerospace products are Georgia’s No. 1 export and the state has more than 800 companies supporting aviation, manufacturing, research, maintenance, repair, and operations.  Many aerospace and engineering positions rely on skilled technical workers whose training pathways do not require a four-year, or advanced degree. There are significant gaps in technical roles such as machinists, electronics technicians, test operators, and systems integrators. These shortages are driven by an aging workforce and a projected national shortfall of at least one million skilled technical workers by 2030. (National Academics of Sciences, Engineering, Medicine, 2025). The gap also stems from the rapid pace of technological advancement, where even current skills can quickly become obsolete if not constantly renewed.  All this combines to create an urgent need for training to support new and sustainable aerospace career pathways. 

Stephen Ruffin, interim chair of the Daniel Guggenheim School of Aerospace Engineering and GSGC director will serve as the principal investigator (PI).  Jud Ready, executive director of SRI; Lori Skillings, GSGC; Hossein Taheri, Georgia Southern University; and Steven Ferguson, GTMI, will serve as co-PIs. Jeffrey McNabb, a research engineer in Georgia Tech’s Aerospace Systems Design Lab (ASDL), will serve as the program manager, leading day-to-day operations and coordinating the project team.

"This initiative strengthens Georgia's position as a leader in aerospace innovation and manufacturing while providing new opportunities for students and industries across the state," said Ruffin.

Coordination between public education systems, industry, and workforce agencies can sometimes be limited. SE-STARS will act as a "hub" to bridge these gaps, connecting Georgia Tech and its specialized research institutes with TCSG’s 22 colleges and 88 campuses to provide statewide access to training.
“Another advantage of the program is the stronger network it creates,” said Ruffin. “Each organization in the SE-STARS team has unique capabilities but together we will strengthen the technical workforce pipeline across Georgia and the broader Southeast.”

The SE-STARS team will collaborate with industry partners to develop curriculum aligned with workforce needs. “The easily ported curricula we develop will be tailored for other institutions to adopt directly, creating a consistent foundation of skills and competencies that employers can universally expect from program graduates across Georgia,” Ready said.

Students will access training through a statewide network of technical colleges serving as regional instructional nodes, which offer flexible online options and hands-on paid apprenticeships to ensure broad geographic reach. 

The program also reaches K-12 and adult learners through career academies and specialized STEM labs, creating a structured, sustainable transition from early education to high-demand aerospace credentials. GTMI will support this work through its Advanced Manufacturing Pathways Program, which connects industry-informed training with pathways into high-demand advanced manufacturing careers.

“Georgia's expanding aerospace and space sectors are creating high-paying jobs and driving economic growth,” said Ruffin. “This program will help develop the skilled workforce needed to support that growth and Georgia’s competitiveness in the space economy.” 

Organized by the Georgia Forestry Foundation (GFF) in partnership with the Ray C. Anderson Center for Sustainable Business at the Georgia Tech Scheller College of Business, Clemson University, and the University of Georgia (UGA) Warnell School of Forestry and Natural Resources, the trip brought together university researchers, foresters, potential carbon credit buyers, and family landowners. 

Georgia is the number one forestry state in the country, with more than 22 million of its roughly 24 million forested acres held in private hands. According to the Southern Group of State Foresters, forests and the forest products industry in the Southern U.S. provide for more than 18% of the world’s pulpwood for paper and paper-related products and 7% of the world’s industrial roundwood. The timber industry also supports thousands of rural livelihoods and sequesters enormous amounts of carbon. Yet today, Georgia forests are under pressure due to natural disasters and market changes. 

The field tour promoted a Georgia-specific carbon exchange that has the potential to save forests, help companies purchase high quality carbon credits, and provide co-benefits for the entire state. 

Pressure Points: Helene’s Wake and Market Headwinds 

Across pine-forested Southeast Georgia, the devastation left by Hurricane Helene remains impossible to miss. A year and a half later, the cleanup – which is slow, expensive, and disheartening – is still ongoing across thousands of acres. Downed timber, too old to be sold for profit, lies in heaps. Throughout the field tour, landowners and foresters shared personal narratives that made it easy to feel the weight of what has been lost. 

Helene only worsened troubles that were already underway. The markets for timber and pulpwood have been weakening. Demand for paper products has fallen sharply, taking pulpwood prices with it. In the last year alone, three mills have closed in Georgia. 

Do I bother to replant? If I plant, will someone actually buy my timber in 20 years? These are the questions landowners across Georgia are wrestling with. Landowners’ decisions today can lead to a future with fewer forested acres, less healthy forests, and forests converted to development – a loss that is permanent. 

The pressing question throughout the field tour was: What happens next? 

Storytelling Matters: The Power of the Personal 

One of the benefits of a field tour is the chance to hear firsthand, personal accounts from the people whose livelihoods depend on forests. 

The tour began in Emanuel County at the Willie Hodges Family Farm Estate. Herbert Hodges welcomed the group to the 600-acre property his family has stewarded for four generations. Hodges shows his respect for the land through thoughtful stewardship – for which he was honored when he was named 2025 Conservationist of the Year by the Georgia Association of Conservation Districts. However, Hodges worries whether the fifth generation will keep the land, and he wants to demonstrate to his heirs that the land is worth holding onto. He remembers his father telling him, “Never get rid of the land. As long as you keep it, you have somewhere to live, somewhere to go.” 

Matt Hestad, senior vice president of GFF, said, “Mr. Hodges has to identify new opportunities for his property not only to keep his family engaged but also to prove the land is economically valuable, both today and into the future.” 

The carbon exchange, if built well, could be exactly that kind of new opportunity. 

Building a Georgia Carbon Exchange 

The initiative to develop a Georgia Carbon Exchange, launched in 2025, is being led collaboratively by the organizers of the field tour. It’s designed to create a voluntary carbon credit marketplace specifically tailored to Georgia’s forest landscape, Georgia’s landowners, and companies that are interested in purchasing high quality carbon credits. 

David Eady, director of industry engagement at the Ray C. Anderson Center for Sustainable Business, described the vision: “We're looking at creating a marketplace for companies doing business in Georgia or headquartered in Georgia, so they can acquire credits that specifically benefit local communities and ecosystems. We want to make sure that we can continue to manage our valuable forest resources that make up well over half of the land in Georgia.”   

“Companies are concerned about sustainability because their customers are – and one of the things that that's manifested is a market for carbon credits,” said Leslie Boby, director of the UGA Southern Regional Extension Forestry. “Being in forestry, we have the original carbon sequestration system: trees. And we have a lot of trees in Georgia.” 

The foundation for the Georgia Carbon Exchange already exists, waiting to be built on. 

All the Players at the Table 

The January tour was a pilot that can be replicated for other groups of potential carbon buyers, policymakers, and stakeholders who need to understand what is at stake in Georgia’s forests before they can meaningfully invest in their future. 

Hestad described what made this first tour valuable: “We need all the players at the table: academics, buyers, and landowners. I feel like we’ve learned from a variety of people about forest management – from a private family landowner about intergenerational challenges, from a recreation-focused landowner about wildlife management, and from landowners who have been impacted by Hurricane Helene. We’ve been provided with context for how a carbon exchange could serve those different sectors of landowners.” 

For industry representatives on the tour, the experience was eye-opening. They joined the tour to learn more about recovery efforts, community support, and the mechanics of a carbon exchange. At the end of the tour, they said they had a clearer sense of both the urgency and the opportunity. 

Clay said, “Landowners are focused on the economics of forestry, and buyers are looking for quality credits. I think there's a lot of opportunity for both of these things to happen.” 

A successful carbon exchange requires trust, understanding, and shared purpose to be cultivated deliberately. Tours like this one are part of that cultivation. 

A Common Goal in Focus 

Georgia has everything it needs to make a carbon exchange work: the forests, the science, the institutions, and the will. What it needs now is exactly what the field tour was designed to build: awareness, connection, and shared commitment among the people and organizations whose decisions will shape the future of the state’s forests. 

Zach Johnson, procurement manager at Beasley Timber Management, LLC, told the group: “With every one green ton of tree growth, you sequester approximately one metric ton of carbon dioxide from the atmosphere. Let’s find a way to certify this wonderful resource we have and prop up these jobs in Georgia – before it’s too late.” 

Maintaining Georgia’s forests is not only about carbon. Well-managed forests filter water, support native wildlife, improve air quality, protect public health, and provide opportunities for outdoor recreation. These are co-benefits that a carbon credit does not fully capture but that are very much part of the value proposition for maintaining Georgia’s private forests. As stated by Yanshu Li, associate professor of forest economics at UGA: “If we take care of our forests, our forests will take care of us.” 

Among the pines of Southeast Georgia, a common goal came into focus. The forests are worth saving. And the right people are coming together with the right plan to make it happen. 

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 manufacturing systems become more connected, the cyberthreat grows with them. Saman Zonouz has spent years documenting how vulnerable smart manufacturing environments are. He’s an associate professor in the School of Cybersecurity and Privacy and the School of Electrical and Computer Engineering, where he co-leads the Cyber-Physical Security Lab with Raheem Beyah, Georgia Tech’s provost and executive vice president for Academic Affairs. 

The answer is yes. Ozdemir demonstrated the technique by taking a piece of paper with a small Waldo-shaped hole cut out and placing it over the page. The demonstration confirms that Waldo is on the page without revealing his location or other details and is a simple example of a concept called a zero-knowledge proof.

In computer science, zero-knowledge proofs allow one person to prove that something is true without revealing the information that makes it true.

These types of problems sit at the center of Ozdemir’s work. As a computer scientist and cryptographer, he studies ways to use mathematics and computer programs to protect information. But his work goes beyond creating new methods for keeping data secret. He is interested in connecting those methods to the computer systems that use them.

“I get excited about what no one else is working on,” he said. “What I’m excited about now is how you relate the security of a computer system to a crypto scheme.”

Two recent papers published at USENIX Security show how Ozdemir is applying this approach to real-world privacy and security problems.

One of these problems is how to handle sensitive information without revealing it.

Imagine two organizations want to combine or analyze information, but neither wants to share its private data with the other. Cryptography can make this possible, but some of these privacy protections can be slow and difficult to use with large amounts of information.

Ozdemir and his collaborators developed a new system called FLOSS (Fast Linear Online Secret-Shared Shuffling) to make one of these tasks much faster.

FLOSS allows two parties to mix a set of private information without either party seeing the original data or learning the final order. This process, known as shuffling, is useful in privacy-preserving applications such as data analysis, anonymous messaging, and private advertising.

In tests, FLOSS shuffled more than one million items in less than half a second, making it more than 800 times faster than previous leading methods.

FLOSS achieves much of this speed by doing some of the hard mathematical work in advance, before the actual data is available. When the data arrives, the system can complete the shuffle quickly, with very little communication between the two computers.

The system is designed to protect against cheating. If one of the parties tries to manipulate the process or access information it shouldn’t, FLOSS can detect the problem and stop the computation.

The researchers also used FLOSS to create a faster way to sort private information. Sorting is a basic computer task but doing it while keeping the information secret can be expensive. Making that process faster could allow privacy-preserving tools to handle much larger amounts of data.

Ozdemir tackled another problem through a project called Orbit: How can computers perform useful work on information that remains encrypted?

Fully homomorphic encryption, or FHE, is a form of encryption that allows computers to perform calculations on protected data without first decrypting it. For example, a hospital could send encrypted medical information to a cloud service for analysis without the service seeing the patients' records.

The challenge is that this type of computing can be extremely slow.

Orbit is a computing tool called a compiler that helps make these encrypted calculations more efficient. A compiler takes computer code and turns it into instructions that a computer can run. Orbit examines an entire computation and identifies more efficient ways to handle some of the most expensive steps in fully homomorphic encryption.

Rather than treating those steps separately, Orbit looks at how they work together and identifies opportunities to reduce the amount of work the computer must do.

In tests, Orbit was between 1.19 and 1.73 times faster than previous leading systems on the workloads studied, including complex tasks such as running artificial intelligence models. The calculations also remained within 0.3% of the accuracy of those performed on unencrypted data.

For Ozdemir, projects like FLOSS and Orbit are part of a broader goal: making advanced cryptography practical enough to use with the computer systems people use every day. 

Now at Georgia Tech’s School of Cybersecurity and Privacy (SCP), Ozdemir is recruiting Ph.D. students from across the computing stack to work with him. He was drawn to Georgia Tech in part for its multidisciplinary approach to security.

“I also just love being around universities,” he said.

At SCP, Ozdemir plans to continue exploring programmable cryptography across the computing stack, integrating cryptography, compilers, and automated reasoning to address security problems from multiple angles. He received his Ph.D. at Stanford University and bachelor's degree from Harvey Mudd College. 

As part of the existing Georgia Traffic Management Center (TMC), those systems notify drivers of changing highway conditions, operate traffic management devices, and help the Georgia Department of Transportation (GDOT) identify and respond to traffic issues requiring immediate attention.

In December 2025, Georgia Tech cybersecurity researchers began working with GDOT to ensure the security of those networked systems and devices. As part of this advanced cybersecurity project, they are applying machine learning (ML), a type of artificial intelligence (AI), to safeguard existing systems and set the stage for future automation.

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

Instead of becoming steadily stickier as they are pulled apart, soft hydrogels first become less adhesive and then more adhesive as the pulling speed increases, revealing a previously unknown "sweet spot" where detachment is easier. The discovery challenges a long-held assumption in adhesion mechanics and reveals a new physical mechanism that governs how soft materials attach and detach.

"We expected the adhesion to increase continuously with pulling speed, as predicted by classical theories," said Yuhang Hu, associate professor in the George W. Woodruff School of Mechanical Engineering and the School of Chemical and Biomolecular Engineering. "Instead, we found the exact opposite over a broad range of speeds. That told us there had to be a completely different physical process at work."

Read the full story.

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. 

"One of the goals of the program is to give students the time and support needed to make meaningful progress on their dissertation research while helping them understand the broader policy, economic, and societal implications of their work," said Laura Taylor, director of EPIcenter.

The stipends enable participants to focus exclusively on clearly defined research goals. The program also supports peer discussions, communication training, and interdisciplinary learning opportunities designed to strengthen both their research and professional development.

This year's cohort explored topics ranging from electricity markets and air pollution to critical mineral supply chains and grid modernization, highlighting the breadth of energy-related research taking place across Georgia Tech.

Exploring Complex Energy Challenges

Ana Mazmishvili, who studies environmental and energy economics, used the summer to examine how climate policies affect communities across state lines.

"My research measures who is actually exposed to pollution from power plants when some states adopt climate regulations to cut emissions while neighboring regions do not," Mazmishvili said. "Because air doesn't stop at state borders, the key question is what happens once the pollution is emitted, and who ends up breathing it."

Her work focuses on the Regional Greenhouse Gas Initiative (RGGI), a cap-and-trade program in the Northeast, and investigates whether the benefits and burdens of emissions reductions are distributed equitably between regulated and neighboring states.

Mazmishvili said the program provided valuable time to focus on her job-market paper, a central component of her dissertation.

"The regular meetings with the program director and other fellows create useful accountability checkpoints and let me hear perspectives from people in very different fields," she said. "We're also learning how to make academic research understandable to a general audience, a skill I expect to use well past this summer."

Industrial and systems engineering doctoral student Faeze Fahimi Aghda spent the summer developing an optimization model for the U.S. gallium supply chain, a critical component of many advanced technologies.

Her research uses mathematical modeling to examine where and when domestic gallium processing facilities should be established under the threat of supply disruptions.

"Working on my research through EPIcenter has taught me to look at my problem from a policy point of view rather than focusing only on the math," Fahimi Aghda said. "The feedback within the meetings helped me improve my model."

Ryan Anthony, in the Jimmy and Rosalynn Carter School of Public Policy, explored how one of the largest oil shocks in U.S. history affected electricity customers and whether utility ownership influenced the impact on consumers.

"So far, my research suggests that it mattered a lot,” Anthony said. “Municipal utilities held rates down and absorbed many of the costs, while private, investor-owned utilities passed more costs through to their customers."

Anthony said the program provided critical support for the archival research required for the project.

"My project depends on data that only exists in old government reports, and that kind of archival work is difficult to fund," he said. "EPIcenter gave me the time and space to do it properly."

Connecting Research to Real-World Impact

For Samin Alipour, the summer provided an opportunity to explore how electric grids can adapt to growing numbers of distributed energy resources.

"Most electric distribution systems were built like one-way roads, carrying power from a substation to homes and businesses," Alipour said. "Rooftop solar, batteries, and electric vehicles are turning those roads into two-way systems."

Her research examines how these emerging technologies can be coordinated to increase grid flexibility and clean energy adoption while maintaining safety and reliability and ensuring that costs and benefits are distributed fairly.

With support from EPIcenter, Alipour focused on the economic and policy dimensions of those challenges. "I did not want my research to remain only a technical model," she said. "The program has helped me connect the technical results of my dissertation to economic value, reliability, equity and compensation policy."

One study developed during the summer was accepted for presentation at a specialized power systems conference, an achievement Alipour credits in part to the opportunity to focus on the broader implications of her work.

Building the Next Generation of Energy Scholars

Beyond advancing individual research projects, the Summer Research Program encourages students to engage with colleagues from different disciplines and develop skills for communicating complex ideas to broader audiences.

“Through regular cohort meetings, participants build a community of accountability, discuss research challenges, explore interdisciplinary energy topics, and develop communication skills,” said Gil Gonzalez, program support coordinator for EPIcenter. “Students also write a research-focused blog post for EPIcenter and present their work at the program's fall workshop, which allows them to share their research with the broader Georgia Tech energy community.”

As EPIcenter continues to support interdisciplinary energy scholarship at Georgia Tech, the Summer Research Program equips future leaders with the tools to address complex energy challenges through technological innovation, informed policy, and economic analysis.

Shreyes N. Melkote, Morris M. Bryan Jr. Professor in the George W. Woodruff School of Mechanical Engineering and executive director of the Novelis Innovation Hub at Georgia Tech, has been named interim associate vice president of Corporate Engagement, effective Sept. 1. He will report to Executive Vice President for Research Tim Lieuwen and will lead the Office of Corporate Engagement (OCE) during a national search for the position’s permanent successor. 

Read more »

Join Georgia Tech undergraduate Harrison Burnside on this latest episode of Engineered at Tech as he tours Katherine Graham's lab and discovers how to track pathogens in the Chattahoochee River. The goal is to help local agencies pinpoint sources of pollution in rivers and reservoirs to protect public health. 

Watch the video on the COE News page

Launched in 2025, INNS serves as a hub for neuroscience and neurotechnology research, connecting researchers across disciplines to advance discovery, innovation, and societal impact.

“A core part of INNS's mission is helping people find one another, connect around shared interests, and build something bigger than they could accomplish alone,” says Executive Director Christopher Rozell. “Simon has spent his career bringing together people, perspectives, and disciplines to tackle complex challenges. I can't think of a better person to help lead our interdisciplinary research efforts and support the next generation of collaborative neuroscience research.”

A longtime leader in Georgia Tech's neuroscience community, Sponberg helped shape the institute's early foundations through the Neuro Next Initiative, which evolved into INNS. As associate director, he will help guide research strategy, foster new collaborations, and support interdisciplinary work across the neuroscience ecosystem.

“Neuro-related research touches so many fields that we inevitably have a problem of finding all the potential right people and opportunities to tap into,” he said. “A core responsibility of this role is helping catalyze the ideas of new teams of talented researchers, educators, and trainees from inception to realization.”

Sponberg is the Glen Robinson Professor in Complex Systems with appointments in the School of Physics and the School of Biological Sciences, where he directs the Agile Systems Lab. His work also connects him to the Institute for Bioengineering and Bioscience (IBB) and the Institute for Robotics and Intelligent Machines (IRIM), underscoring the cross-disciplinary approach that defines both his research and leadership.

Since joining Georgia Tech in 2014, he has built a highly collaborative research program spanning neuroscience, biology, physics, engineering, and robotics while helping foster interdisciplinary connections across campus. He currently leads a Multidisciplinary University Research Initiative (MURI) that brings together neuroscientists and engineers from five universities to understand how brains achieve fast, flexible perception and decision-making in complex sensory environments. He also co-leads the Integrative Movement Sciences Institute, an NSF Biological Integration Institute focused on understanding movement and muscle function across scales.

His contributions have been recognized through numerous honors, including a Young Investigator Award from the International Society for Neuroethology, a Klingenstein-Simons Fellowship in the Neurosciences, and the Leddy Family Dean’s Faculty Excellence Award.

As associate director, Sponberg will focus on helping researchers identify new opportunities for connection and collaboration. In addition to overseeing seed funding programs, he hopes to create pathways for researchers to build teams, access support resources, pursue ambitious interdisciplinary research ideas, and team with Georgia Tech’s undergraduate and graduate neuroscience degree programs.

“I look forward to being a resource for our community when people are looking for help in building teams or finding opportunities to support their ideas,” he said. “Bring your best ideas and please reach out if you want to talk about ideas in the interdisciplinary neuro space that you want to see realized.”
 

Counterfeit and out-of-spec components are entering U.S. defense supply chains through thousands of small and midsized suppliers that make up the lower tiers of the industrial base. Researchers at the Georgia Tech Manufacturing Institute (GTMI) say the fix isn't just better parts, but better proof: verified digital records, secured against tampering, that travel with each component from raw material to installation.   

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

The U.S. has seen its printed circuit board market share plummet to 4% while becoming dangerously dependent on foreign rare earth processing. Now, with global supply chains fracturing, defense industrial capacity under pressure, and adversaries looking to dominate advanced production, the country is in a race to rebuild — and to rebuild smarter. 

The Air Quality Index (AQI) measures how clean or polluted the air is. A healthy AQI is between zero and 50, but when wildfire smoke blows in and settles over cities, the AQI can reach levels of 500 or more. Poor air quality changes where and how people spend their time and money, reduces productivity (even for those working indoors), and increases healthcare costs.

“Environmental regulations like the Clean Air Act dramatically improved our air quality over the past 40 years, but as wildfire season becomes the new normal, wildfire smoke is eroding those gains,” Wichman said. According to recent research, wildfire smoke has erased about a quarter of the progress made over previous decades, and more than half in many western states. 

Read Full Story on the IAC News Page

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.”

--Written by Anne Wainscott-Sargent

From a single Atlanta church to a growing network across the Southeast, Georgia Tech engineer Sofía Pérez-Guzmán is connecting communities and researchers to support resilience in extreme weather events. 

Instead of becoming steadily stickier as they are pulled apart, soft hydrogels first become less adhesive and then more adhesive as the pulling speed increases, revealing a previously unknown "sweet spot" where detachment is easier. The discovery challenges a long-held assumption in adhesion mechanics and reveals a new physical mechanism that governs how soft materials attach and detach.

"We expected the adhesion to increase continuously with pulling speed, as predicted by classical theories," said Yuhang Hu, associate professor in the George W. Woodruff School of Mechanical Engineering and the School of Chemical and Biomolecular Engineering. "Instead, we found the exact opposite over a broad range of speeds. That told us there had to be a completely different physical process at work."

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

For researchers in Georgia Tech's Cyber-Physical Security (CPSec) Lab, however, the vulnerabilities behind many of these incidents are far from new.

Associate Professor Saman Zonouz leads the CPSec Lab and has studied programmable logic controllers (PLCs) for years. These devices automate critical infrastructure, including water treatment facilities, power grids, manufacturing plants, and transportation systems. The lab’s work has revealed widespread internet exposure and software vulnerabilities that leave many industrial control systems vulnerable to cyberattacks.

"Out of the 16 critical infrastructure sectors defined by the Cybersecurity and Infrastructure Security Agency, four are considered lifelines," Zonouz said. "Of those four, communications, energy, transportation, and water, the water sector is the most vulnerable, which is why it is so often targeted."

PLCs serve as the brains of industrial operations, monitoring sensors and controlling equipment that keep essential services operational.

"Imagine you have a thermostat that controls the temperature of your house. That is a type of controller," Zonouz explained. "The professional version does the same thing in industry."

When these controllers are directly accessible from the internet, attackers can exploit them to disrupt operations, manipulate industrial processes, or interfere with the systems that deliver essential services. Controllers may be intentionally exposed to allow operators to monitor equipment remotely. They can also be unintentionally accessible online because of configuration errors.

However, internet exposure is only part of the problem.

The CPSec Lab maintains a collection of PLCs that researchers reverse engineer to better understand their firmware, communication protocols, and security weaknesses. Their research has found that many controllers contain vulnerabilities that attackers can exploit once they gain access.

"Not only can the attackers see the house they want to rob, but the doors are also left unlocked," Zonouz said.

In 2024, Zonouz and his collaborators presented PLCHound at the ACM Conference on Computer and Communications Security (CCS), introducing an automated system that identifies internet-connected PLCs hidden within massive internet-scale datasets collected by services such as Shodan and Censys. The work was led by Ph.D. student Ryan Pickren. Provost and Executive Vice President for Academic Affairs Raheem Beyah, Assistant Professor Frank Li, and Research Scientist Animesh Chhotaray are co-authors of the study. 

Rather than relying on traditional scanning techniques, PLCHound identifies subtle network signatures that reveal industrial devices that prior methods often missed. Using the system, the researchers conducted one of the largest studies of publicly reachable PLCs from major manufacturers.

Their findings showed that previous estimates undercounted the number of internet-accessible industrial controllers by as much as 37 times. Even more concerning, nearly 96% of the identified devices exposed protocols linked to recently disclosed critical vulnerabilities.

The researchers did more than document the problem. After identifying exposed devices, the team launched a large-scale notification campaign, contacting more than 7,000 industrial operators to alert them that their systems appeared vulnerable. The effort enabled many organizations to investigate and address security issues before they could be exploited.

The recent attacks on municipal water systems reinforce concerns researchers have raised for years: many critical infrastructure operators continue to rely on operational technology designed primarily for reliability and performance rather than for cybersecurity.

Improving those defenses, Zonouz said, will require more than simply patching individual vulnerabilities.

The researchers cite the energy sector as a model. Compared with other critical infrastructure sectors, electric utilities generally operate under more mature cybersecurity requirements and undergo routine compliance audits, providing organizations with greater visibility into the devices connected to their networks and the risks they pose.

Implementing those improvements will not be easy. Many municipal water utilities operate with limited budgets and aging infrastructure, leaving little funding available for cybersecurity investments. As attacks on critical infrastructure become more frequent, the researchers argue that gaining visibility into operational technology assets and strengthening oversight are essential first steps to protect the systems communities rely on every day.

The CPSec Lab is a collaborative laboratory within the School of Cybersecurity and Privacy as well as the School of Electrical and Computer Engineering.

Initial public offering (IPO) filings are dense disclosures submitted to the U.S. Securities and Exchange Commission. They can stretch hundreds of pages and combine legal language, financial data, and visuals like charts and infographics. Even experienced analysts struggle to read them end to end, leaving many everyday investors relying on headlines or summaries. 

New research from Georgia Tech’s Financial Services Innovation Lab reveals how artificial intelligence can make these critical documents more accessible and reveals where AI still has room for improvement. 

“IPO-Mine: A Toolkit and Dataset for Section-Structured Analysis of Long, Multimodal IPO Documents” authors include Michael Galarnyk, Siddharth Lohani, Vidhyakshaya Kannan, Sagnik Nandi, Aman Patel, Liqin Ye, Arnav Hiray, Rutwik Routu, Prasun Banerjee, Siddhartha Somani, and Sudheer Chava. 

Making the Complex Understandable

The authors developed IPO-Mine, an open-source toolkit and dataset designed to break IPO filings into manageable pieces. Instead of treating filings as a single document, IPO-Mine separates them into structured sections and extracts visuals like charts for analysis.

“IPO filings are important public documents, but they are very difficult to work with at scale,” said Siddharth Lohani, a Georgia Tech computer science major ’26, software engineer at Bloomberg, and co-first author of the study. “We wanted to make these filings easier to analyze systematically.”

Why IPO Filings Matter

IPO filings offer investors a detailed look at how a company operates before it goes public.

“IPO filings give investors a clearer look at how a company makes money, what risks it faces, and how it positions itself before entering the public market,” said Arnav Hiray, a Georgia Tech machine learning doctoral student in the Financial Services Innovation Lab, AI for Financial Markets VIP instructor,  and co-author. “Even if everyday investors don’t read the full filing, these documents can help them better understand a company’s prospects.”

For retail investors, that insight can help cut through marketing hype and offer a clearer sense of a company’s underlying strengths and risks.

AI’s Strengths

Research shows that large language models and multimodal AI models can use their speed, scale, and pattern-recognition capabilities to offer significant advantages when analyzing IPO filings, including:

• Processing massive documents: IPO filings can exceed hundreds of thousands of words, making manual review difficult. IPO-Mine structures the filings into sections and extracts visuals for analysis.
• Structuring unorganized data: IPO-Mine standardizes inconsistent sections across filings, making comparisons easier across companies and industries. 
• Analyzing text and visuals together: By extracting charts and images, AI can evaluate not just what companies say, but how they present information visually. 
• Identifying trends at scale: Researchers can analyze patterns in disclosure practices across decades, industries, and thousands of companies.
   

Together, these capabilities could help democratize financial analysis, giving more investors access to insights that were once limited to professionals.

A Key Finding

One of the study’s most striking findings is that IPO filings are evolving in two different directions.

“What stood out was that the text and visuals appear to be moving in different directions,” Lohani said. “Investors and researchers need to pay attention to both.”

The research shows that written sections are becoming more standardized, while visual elements such as charts and infographics are becoming more complex and varied.

“As text becomes more standardized, more of a company’s distinctive story shifts into its visuals,” said Vidhyakshaya Kannan, a Georgia Tech Financial Services Innovation Lab intern and co-author. “Because boilerplate language often looks the same across filings, charts and infographics are increasingly where companies differentiate themselves and make their case to investors.”

For investors, that means understanding a company requires studying the visuals as carefully as the text; figures can’t simply be skimmed or skipped over.

Where AI Struggles

Despite its promise, AI is not yet a perfect solution.

• IPO filings are long: longer documents can reduce model performance, making it difficult for AI to maintain accuracy across an entire filing.
• IPO filings are visual: AI tools struggle to interpret visual data correctly.
• IPO filings are multimodal: filings combine text, tables, and visuals in inconsistent formats. This makes them difficult for AI models to process reliably.
   

“Our results show that even strong multimodal models can disagree with expert human judgments on financial charts, especially when they are misleading,” Kannan said. 

The Future of Financial Transparency

AI can accelerate analysis and uncover patterns, but human judgment remains essential for interpreting the visuals companies increasingly use to tell their story. Even with these limitations, researchers believe tools like IPO-Mine could play an important role in shaping the future of financial transparency.

“IPO-Mine can help researchers, regulators, and investors analyze IPO disclosures more systematically, revealing patterns in how companies communicate risk, performance, and strategy before entering public markets,” said Hiray. 

By making complex financial disclosures more accessible and actionable, AI-powered tools have the potential to broaden access to critical market information and support more informed investment decisions.

Watch the researchers explain IPO-Mine and its impact

Read More: IPO-Mine

Learn More: Center for Finance and Technology

IMS focuses on transformational technologies and societal systems that arise where innovative materials, devices, and processes meet.

“Transformative interdisciplinary research takes time to develop, and a second year of funding gives these teams the opportunity to build on early successes, expand collaborations, and demonstrate the impact of their work,” said Eric Vogel, executive director of IMS. “This continued investment helps researchers establish a strong foundation, achieve key milestones, and position promising initiatives to grow into larger, sustainable research programs capable of attracting significant external support.”

The funded projects come from four colleges and eight schools across Georgia Tech and the Georgia Tech Research Institute (GTRI). IMS selected these projects based on their innovative approaches, potential impact, and alignment with the IMS mission to push the boundaries of science and technology. They will receive funding, access to state-of-the-art facilities, and other support from the institute to bring their research to life.

IMS supports interdisciplinary research both in nationally recognized areas of need and those just emerging. It scaffolds research from the ground up, from seed funding for new initiatives to infrastructure support for research programs and embedded support for research centers. 

The 2026 research initiatives and programs include:

Research Initiatives:

Extreme-Environment Microelectronics | Nima Ghalichechian, John Cressler, Farrokh Ayazi, School of Electrical and Computer Engineering

Multifunctional Materials for Efficient Buildings | Akanksha Menon, George W. Woodruff School of Mechanical Engineering

Precision Agriculture in Controlled Environments | Antonio Facchetti, School of Materials Science and Engineering; Yongsheng Cheng, School of Civil and Environmental Engineering; Anju Toor, School of Materials Science and Engineering

Sustainable Thermoregulation Strategies for Climate Change Resilience | Matthew Flavin, School of Electrical and Computer Engineering; Joe Bozeman, School of Civil and Environmental Engineering; Noura Howell, School of Literature, Media and Communication

Research Programs: 

Autonomous Research for Materials | Mark Losego, School of Materials Science and Engineering; Shreyas Kousik, George W. Woodruff School of Mechanical Engineering; Animesh Garg, School of Interactive Computing

Georgia Tech Center for Semiconductor and Computing | Asif Khan, School of Electrical and Computer Engineering and the George W. Woodruff School of Mechanical Engineering; Divya Mahajan, School of Computer Science and the School of Electrical and Computer Engineering

Research Center:

Quantum Applications Research Center | Martin Mourigal, School of Physics; Robert Wylie, Georgia Tech Research Institute

Learn more about IMS’s research focuses and see a full list of its centers, programs, and initiatives.

With a Ph.D. in biomedical engineering and as a former trainee in the Parker H. Petit Institute for Bioengineering and Bioscience (IBB), it’s no surprise that Georgia Tech alumnus and serial entrepreneur Chris Lee loves numbers. One in four. Eighty percent. Five times.  

Read more »

Read more »

Recycled materials promise a cleaner future, but recycled content alone does not necessarily make a product sustainable. At Georgia Tech’s Daedalus Lab, assistant professor, National Science Foundation CAREER Award recipient, and Brook Byers Institute for Sustainable Systems Faculty Fellow Christos Athanasiou and postdoctoral researcher Danqi Sun are working to provide greater certainty to designers and engineers by rethinking how materials are tested for their fracture characteristics. Their article in Science Advances details a new testing protocol that reduces cost, increases speed, and simulates real-world conditions.

Materials shape nearly every part of modern life, from packaging and consumer products to bridges and medical devices. Choosing the right material involves balancing durability, cost, manufacturability, and environmental impact. Yet those decisions are not always guided by a clear understanding of how materials age and fail under real-world conditions, especially for recycled materials like plastics.

One way that materials frequently fail is by cracking. A small crack can begin almost invisibly. Over time, it can spread from regular wear and tear and exposure to common environmental factors like moisture, temperature fluctuations, or even dirt. Eventually, the crack expands, and the part fails. Engineers have studied fracture for more than a century, but connecting the science of cracking to practical decisions about sustainability remains a major challenge.

The characteristics of recycled plastics often vary from those of the same material in unrecycled, or virgin, form. Products made from recycled plastics may be sold with sustainability claims under the assumption that they will perform as if they were made with virgin material. However, premature failure requiring repair or replacement can quickly change the sustainability equation as well as the acceptance of recycled materials by manufacturers and consumers.

Beyond Conventional Fracture Testing

Materials rarely fail due to a single factor. They may be exposed to several factors simultaneously, such as mechanical loading, chemical environments, temperature changes, moisture, and time. Traditional fracture protocols test one specimen at a time under carefully controlled laboratory conditions, which bear little resemblance to the real world. To move beyond this limitation, Sun developed an in-situ, high-throughput platform capable of studying how materials degrade and fail under more realistic conditions.

The platform changes conventional fracture testing in three important ways. First, it can test multiple specimens simultaneously rather than one at a time. By monitoring samples in parallel, testing time can be reduced by more than 60%. Second, it allows materials to be tested in realistic environments. In this study, researchers examined virgin and recycled plastics in alkaline environments that resemble conditions encountered in applications like landfill liner membranes and geotextiles. Third, the platform incorporates an imaging technique known as photoelasticity, which reveals the formation of stress fields that form around the origin of a newly developing crack. This allows researchers to see cracks develop earlier than before, giving them a clearer picture of the forces that drive crack growth.

The researchers have made the technology available for licensing through Georgia Tech’s Office of Technology Licensing. “Our goal was to make fracture testing not only faster but also more informative,” Sun said. “By combining high-throughput testing, realistic environments, and full-field stress imaging, we can better understand how materials fail under conditions closer to real-world applications.”

An Honest View of Sustainability

Recycled plastics are often viewed as a greener choice. But according to the study, it’s not always so straightforward. If a recycled product fails prematurely and needs to be replaced frequently, its environmental and economic costs can increase despite its recycled content. As Athanasiou puts it, “Failing materials don’t just break products. They can break sustainability promises.”

For example, comparing virgin polyethylene terephthalate (PET) with recycled PET (rPET) in applications such as landfill geotextiles, the researchers discovered that rPET showed lower resistance to environmental stressors, particularly in alkaline conditions over a pH of 9. In this application, specifying rPET over virgin PET would likely eliminate all of the presumed economic and environmental advantages of using a recycled material.

“Recycling is essential, but recycled content alone does not tell the full story. If a material fails too soon, the environmental benefits can disappear,” Athanasiou said.

From Cracks to Circularity

For the researchers, the significance of the work extends beyond recycled plastics. The broader goal is to provide a fast, affordable, and realistic platform for evaluating the sustainability of any material choice. Because current testing protocols are costly, not widely available, and limited in the information they yield, engineers, manufacturers, and policymakers often have little choice but to continue to specify non-recycled materials because they will perform as expected. Having cheap and accurate data on recycled materials will help to accelerate their adoption because matching the engineering properties of recycled materials to their most appropriate applications will become more obvious.

The researchers also hope to expand the platform to simulate even more complex environments and apply it to a wider range of materials. Because the system generates large amounts of detailed data, it may enable opportunities to use computational modeling or artificial intelligence to digitally simulate mechanical testing, driving down costs and expanding availability even more.

The larger vision is a future in which sustainability is judged not by labels or assumptions, but by evidence for how a material performs, how long it lasts, how it fails, and what it costs society and the environment over its full lifetime.

Please visit the Daedalus Lab YouTube channel to see an explainer video about this new testing protocol: https://youtube.com/watch?v=zmRhiRIiAkQ

Read the paper here: https://www.science.org/doi/10.1126/sciadv.aeh0456

This research was supported by the National Science Foundation CAREER Award No. 2338508.

But discovering and vetting those materials can be slow, expensive, and hands-on, requiring researchers to prepare samples, run experiments on specialized equipment, and repeat the cycle through trial and error.

Now, Georgia Tech aims to deliver a paradigm shift in materials and manufacturing research with a new Programmable Cloud Laboratory that will leverage artificial intelligence (AI), simulation, and autonomous experimentation to accelerate that process dramatically.

Built upon Georgia Tech’s Advanced Manufacturing Pilot Facility (AMPF), a core facility of the Georgia Tech Manufacturing Institute (GTMI), the cloud lab will allow researchers across the country to direct work remotely, refine experiments based on results and AI recommendations, and tap into advanced manufacturing capabilities without spending weeks on-site. In effect, the cloud lab will bring the facility to the researcher.

“By making advanced manufacturing and AI-driven experimentation accessible from anywhere, we are accelerating the discovery of critical new materials and shaping the future of U.S. innovation,” said Tim Lieuwen, executive vice president for Research. “Georgia Tech is proud to provide the world-class infrastructure to help meet this national need and strengthen our research partnerships.”

The cloud lab is supported by $18.1 million from the National Science Foundation (NSF) and is part of a broader effort to build a national network of 20 AI-enabled cloud laboratories. The labs are designed to work together, eventually allowing researchers to combine capabilities and workflows across the network. The new research ecosystem will connect advanced scientific infrastructure with expertise across the country.

“Researchers can ask a question, have work recommended by AI agents, have experiments carried out at the facility using robotics, and get the results back,” said Aaron Stebner, GTMI associate director, Eugene C. Gwaltney Jr. Chair, James R. and Sarah R. Borders Faculty Fellow, and professor in the School of Materials Science and Engineering and the George W. Woodruff School of Mechanical Engineering (ME). “They can use AMPF resources to advance their own research without having to be experts in each piece of equipment or send students to AMPF for weeks at a time.”

By lowering costs and barriers to conducting that research, Stebner said, the cloud lab will dramatically expand who can take advantage of AMPF’s capabilities.

A Self-Driving Research Lab

AMPF is a mixed-use facility where both industry and academic partners can discover new materials and do manufacturing research. Today, the facility is approaching autonomous workflow capabilities across about 38 pieces of equipment. Through the cloud lab, the team aims to expand automated and autonomous workflows to more than 100 of AMPF’s 160 pieces of equipment.

The cloud lab will also bring together stages of materials development that have traditionally happened separately, allowing researchers to explore materials discovery, manufacturing, testing, and scale-up within the same research environment.

Pascal Van Hentenryck, director of the NSF AI Institute for Advances in Optimization and A. Russell Chandler III Chair in the H. Milton Stewart School of Industrial and Systems Engineering, said the automation extends beyond individual pieces of equipment. Robots can operate machines and move materials from one station to another, physically carrying out workflows requested by researchers from afar. AI will help determine which machines and robots are needed for each task and manage their movements across the facility.

Van Hentenryck compared the process to following a recipe.

“When you cook, you have a recipe, and the recipe tells you what you have to do,” Van Hentenryck said. “You don’t need to understand exactly how the stove is working. You just need to know what you need to accomplish with it.”

AI agents will take those high-level “recipes” from researchers, translate them into detailed workflows, and coordinate experiments, simulations, and data flows across the facility.

The system will rely in part on digital twins — virtual models of the facility that can help plan, monitor, and improve experiments before and during execution. Van Hentenryck said the system is also designed to learn from each run, improving how machines are tuned and how future workflows are scheduled.

The project will integrate Duke University’s Automatic FLOW for Materials Discovery software platform, led by professor Stefano Curtarolo, to connect computational discovery with physical experimentation and help researchers more rapidly identify and evaluate promising new materials. Contextualize, led by founder and CEO Branden Kappes, will provide the data platform that seamlessly connects researchers, instruments, data, and IT systems across the distributed network. Tech AI will also contribute to the project as part of the broader research team.

The cloud lab will help bridge a longstanding gap between research and industrial adoption. Companies can be reluctant to interrupt working production lines to test unproven technologies, while startups and academic researchers often lack access to industrial-scale facilities where they can demonstrate that their ideas work. AMPF provides an environment where emerging technologies can be tested and de-risked without disrupting commercial production.

“The cloud lab will give industry partners and manufacturers the ability to evaluate new ideas before they commit to large-scale deployment,” said Tom Kurfess, executive director of GTMI and Agustin A. Ramirez/HUSCO International Distinguished Chair in Fluid Power Systems in ME. “This initiative will shorten development cycles and make it easier to bring promising technologies into production, enabling our partners and us to innovate at the speed of thought.”

Expanding Access to Advanced Research

The project aims to serve more than 400 users from 150 academic, industry, and government institutions, with more than half participating remotely.

“Making these autonomous labs available to a very wide community is key to innovation,” Van Hentenryck said. “You just give a lot of people the opportunity to try things out.”

The cloud lab builds on a larger effort Georgia Tech has pursued through AMPF for years: integrating AI, automation, and advanced manufacturing to create a flexible research environment that can evolve with technology, expand access, and strengthen U.S. leadership in materials and manufacturing.

For Stebner, the cloud lab represents a critical next step in bringing that vision to life.

“We are six years into this effort, and we’re already at a place I thought would take us 20 years to reach,” Stebner said. “This cloud lab is going to take us to a level of technology, research, leadership, and access that I didn’t know if we would reach by the end of my career.”

CultivAgents is a three-agent system that fields gardening questions and creates tailored plans based on a user’s gardening skill level, climate and environment, and cultural background.

The experience agent, environmental agent, and ethnobotanical agent inform one another and work together to guide users through the gardening process.

“Multi-agent systems provide multi-faceted support,” said Diana Wang, a Ph.D. student in Georgia Tech’s School of Interactive Computing who created CultivAgents. “My interest was in how we could provide more personalized and aligned support to individuals trying to grow food themselves while facing unique environmental or cultural factors.”

Gardening is a hobby that many people start but give up because of the time and effort it requires to be successful. Ryan Pemberton, a horticulturist at Georgia Tech’s community garden, said the two biggest mistakes he sees novice gardeners make are starting too big and overwatering.

“If you’ve never gardened before, trying to manage a large plot could be overwhelming,” Pemberton said.

“You can start small. You don’t have to have a big garden right away. You can start with one tomato plant and grow from there. See how well you can keep that one plant alive and then expand as you feel comfortable.”

Aside from the built-in health benefits of growing fresh food and working outdoors, Pemberton said gardening can lower your grocery bill and reduce carbon emissions by minimizing food transportation. 

It can also be a great way for international students at Tech to grow foods native to their homelands. He said a tool like CultivAgents could be useful for determining whether Atlanta’s climate is suitable. 

“People might want to grow a lot of different vegetables in their garden, but if you go too far south of here, it gets a little too hot to grow things like broccoli and strawberries,” he said. 

“A little north of here, it gets a little too cold to grow some species of peppers. Having something tell you what grows well in your region means you’re not having to pick and choose or guess.”

That’s one of the reasons Wang designed CultivAgents to feature multiple agents that consider unique environmental and cultural contexts.

“Multiple agents help distribute specific types of support as opposed to the generic support you often get from a single chatbot,” Wang said.

“Another advantage is that they tend to build on each other. The environmental agent builds on the experience agent’s detailed steps. This allows the system to tell you how to grow bush beans, for example, within a specific local community.”

Wang said she surveyed and interviewed new and experienced gardeners who use Tech’s community garden to learn what they would want from a conversational agent. She found that many wanted step-by-step instructions and guidance on what to plant, how to plant it, and a schedule for upkeep.

“All of our users told us they view gardening as something that’s long term, so they wanted this platform to be able to facilitate that kind of relationship,” she said.

The community garden is a shared space with nine garden beds. Pemberton said it’s a great place for new gardeners to learn to grow food before starting their own gardens. Much of the food grown there is donated to Klemis Kitchen, Georgia Tech’s on-campus food bank.

For more information about the community garden and how to get involved, visit https://sustainability.campusservices.gatech.edu/community-garden/

To see a live demo of CultivAgents, visit https://cultivagents.onrender.com.

The Institute for Matter and Systems (IMS) at Georgia Tech has announced the Spring 2026 Core Facility Seed Grant recipients. The primary purpose of this program is to give graduate students in diverse disciplines working on original and unfunded research in micro- and nanoscale science and engineering the opportunity to access the most advanced academic cleanroom space in the Southeast. In addition to using the labs' state-of-the-art fabrication, lithography, and characterization tools, the awardees will have the opportunity to gain proficiency in cleanroom and tool methodology and access the consultation services provided by research staff members in IMS. Seed Grant awardees are also provided travel support to present their research at a scientific conference. 

Through a major investment from the U.S. Department of Energy (DOE), Georgia Tech is helping accelerate the development of domestic critical minerals from unconventional and secondary resources. The $7.5 million award positions the Institute to advance supply chain solutions that span resource discovery, processing, recycling, and circular materials management.

Selected by DOE’s Office of Critical Minerals and Energy Innovation, Georgia Tech will lead the Critical Minerals in the Atlantic Seaboard Plain (CM-MAP) project. The regional effort builds on DOE’s Carbon Ore, Rare Earth, and Critical Minerals (CORE-CM) initiative and will examine potential resources across the Atlantic coastal plain.

The CM-MAP project will focus on sedimentary deposits, including kaolin, bauxite, heavy mineral sands, and phosphates, as well as legacy mining residues, coal combustion byproducts, and other unconventional and secondary resources that could support future recycling and circular economy opportunities.

Drawing on existing infrastructure, regional assets, industry bases, and scientific expertise, CM-MAP will establish a regional innovation ecosystem that supports domestic critical mineral production, recycling, and advanced manufacturing, while fostering new economic opportunities throughout the Southeast.

“This is a powerful example of how Georgia Tech brings together leading research capabilities and partnerships from industry, government, nonprofits, and national labs to address complex national challenges,” said Tim Lieuwen, executive vice president for Research. “By identifying and domestically sourcing critical minerals, we are helping secure essential supply chains, while enabling the next generation of energy and materials technologies.”

The DOE award builds on a growing network of research, industry, regional, and international partnerships led by Georgia Tech to translate scientific discovery into real-world supply chain solutions, including:

• Research leadership — Founded in 2024, Georgia Tech’s Center for Critical Mineral Solutions serves as a hub for interdisciplinary research and technology development across the Institute.
• Regional partnerships —Through the Georgia Partnership for Essential Materials, a flagship regional collaboration platform, Georgia Tech, the University of Georgia, Georgia State University, and the Georgia Mining Association convene stakeholders from across the critical minerals sector. The partnership brings together industry, nonprofit organizations, regional economic development agencies, national labs, universities, and technical colleges to connect, collaborate, and stay engaged in the latest developments.
• International engagement — A U.K.-U.S. working group extends partnerships across the Southeastern United States and Southwest United Kingdom, connecting researchers, industry leaders, and government agencies working to strengthen global supply chains.
• Georgia Critical Mineral Supply Chain Manufacturing Demonstration Center — Supported through congressional funding, the center is developing capabilities and regional supply chain demonstrations that connect resource development, materials processing, recycling, and advanced manufacturing.

As part of CM-MAP, researchers will analyze materials collected from natural deposits and industrial sites throughout the Southeast to identify their critical mineral content. The resulting large datasets will be combined with artificial intelligence and machine learning approaches to better understand and predict where resources exist, optimize extraction pathways, and inform future recovery and recycling strategies.

“This project brings together a highly collaborative team from Georgia Tech, national labs, industry partners, and research institutions across the region,” said Yuanzhi Tang, the principal investigator and Georgia Power Professor in the School of Earth and Atmospheric Sciences, with a courtesy appointment in the School of Civil and Environmental Engineering.

Tang is also the founding director of the Center for Critical Mineral Solutions and executive director of the Strategic Energy Institute. 

“Through this award, we are working to build secure and resilient critical materials supply chains, from resource discovery and characterization to processing, recovery, recycling, and advanced manufacturing, while also developing the skilled workforce needed to support these emerging industries,” Tang said. “Our vision is to create a regional innovation ecosystem that embraces both unconventional resources and circular economy approaches to maximize the value of materials already in use.”

Learn more about critical materials research and workforce development efforts at Georgia Tech by visiting the Center for Critical Mineral Solutions webpage.   

When most people think of hurricanes, they picture howling winds tearing off roofs and snapping trees. But for Ali Sarhadi, a Brook Byers Institute for Sustainable Systems (BBISS) Faculty Fellow, assistant professor in the School of Earth and Atmospheric Sciences, and director of the Climate Risk and Extreme Dynamics Lab, the real killer is often less visible. “People think that hurricanes are about wind, but sometimes that’s not the whole story,” he said. “The majority of fatalities are coming from the water, not the wind.”

Supported by two Sustainability Next Seed Grants, Sarhadi’s work draws on climate science, fluid physics, engineering, and artificial intelligence. He’s using AI-powered, physics-informed models to better anticipate water hazards that can cripple cities and power grids in both coastal and inland communities.

Rethinking Hurricane Risk

Sarhadi focuses on compound flooding, the dangerous interaction between storm surge, torrential rainfall, and river flooding that increasingly defines hurricanes. He points to Hurricane Mitch, which hit Central America in 1998, as a stark example, noting that more than 12,000 people died, “all from freshwater flooding — none from wind,” he said.

His work has shown how climate change and sea-level rise are reshaping flood risk from storms like Hurricane Sandy, which devastated New York and New Jersey in October 2012. In the current climate, a Sandy-level natural disaster has a recurrence period of roughly once every 150 years. But that is changing fast. “Because of climate change and sea-level rise, by the middle of this century, the same level of flooding is likely to occur once every 60 years. By the end of the century, that goes up to once every 30 years,” he says. “Hurricane Sandy caused about $70 billion in damage. Imagine experiencing that kind of destruction every 30 years.”

Since 1970, Sarhadi notes, damage from tropical cyclones has increased by about 380% globally, a trend driven by the combined effect of stronger storms and more people and infrastructure being located in harm’s way.

Physics-Informed AI: Street-Level Flood Warnings

While storm forecasting has improved dramatically in recent decades, Sarhadi argues, “We’re in good shape in terms of track forecasting, and we’re getting better at rapid intensification forecasting. But what is missing is the hazard part, and specifically the water part. That’s the number one killer.”

His lab is developing AI models tightly coupled with physics-based simulations to forecast hurricane-induced flooding at unprecedented resolution.

Using Hurricane Sandy as a test case, his team showed that by integrating physics-based surge and rainfall models with generative AI, they could forecast building-level flood depths three to five days before landfall. “We could predict that a storm was surge-dominant and estimate how much flooding could happen at the level of each building with an accuracy beyond 90%,” he says.   

Those extra days, and that level of granularity, could give emergency managers and local leaders the information they need to order earlier evacuations, pre-stage resources, and protect critical infrastructure. “We hope by combining AI and physics-based models we can come up with faster, more accurate modeling, first, to save lives, and then to minimize the economic damage,” Sarhadi says.

Targeting Georgia’s Coastline 

Although much of the public’s attention focuses on the Gulf Coast and megacities on the Eastern Seaboard, Georgia’s coastline is also highly vulnerable to surge and compound flooding. Sarhadi is collaborating with Georgia Tech for Georgia’s Tomorrow to model risk in places like Savannah and the surrounding coastal region. “We’re working to come up with good long-term solutions for protecting coastal communities and infrastructure,” he says.

Events like Hurricane Helene in 2024, which triggered extended blackouts in Georgia and lethal flooding in western North Carolina, underscore how far inland these risks can reach. “People think hurricanes are just a problem for coastal areas,” Sarhadi says. “But even if you are far from a coastline, you can be at risk when saturated soils, torrential rain, and river flooding combine.”

Building Climate-Resilient Power Grids and Cities

Sarhadi’s work doesn’t stop at forecasting. A central focus of his research is climate-resilient infrastructure, particularly the power grid. His team is exploring digital twin modeling — virtual replicas of energy and infrastructure systems. “When you have a digital twin of your grid, you can run that hurricane through it and identify which substations or power lines are more vulnerable,” he says, explaining that this knowledge could trigger utility crews to fix or reinforce power lines ahead of storms.

Looking decades ahead, these tools could help utilities and planners prioritize where to upgrade aging infrastructure as hurricanes intensify and water levels rise. “We know hurricanes are getting more intense, and our infrastructure is aging,” Sarhadi said. “By combining engineering, climate science, and AI, we’re trying to design better adaptation plans so our communities and power systems are more resilient in the future.”

The ACS is one of the world’s largest scientific societies, and its Fellows Program recognizes outstanding achievements in scientific research, education, leadership, and service to the chemical profession and honors a select group of members each year.

"Election as an ACS Fellow is a significant honor that recognizes not only scientific excellence but also leadership and service to the profession," said Julia Kubanek, Georgia Tech's vice president for Interdisciplinary Research. "Yuanzhi's pioneering research, her leadership within ACS and the Strategic Energy Institute, and her commitment to advancing interdisciplinary collaboration have strengthened Georgia Tech's impact in chemistry, energy, and environmental research. We are proud to celebrate this well-deserved recognition."

Tang was recognized for her contributions to environmental chemistry, biogeochemistry, and energy-related research, as well as for her leadership and service to the chemical sciences.

"Given her exceptionally energetic research program, which spans topics ranging from the basic understanding of chemical cycling on Earth to creative solutions to recover rare elements from wastes, this honor is richly deserved and completely unsurprising," said Jean Lynch-Stieglitz, chair of the School of Earth and Atmospheric Sciences. "We are lucky to have Yuanzhi as part of EAS."

As SEI executive director, Tang leads Institute-wide efforts to strengthen Georgia Tech's energy research enterprise by connecting expertise across disciplines and fostering partnerships with industry, government, and national laboratories. She also maintains an internationally recognized research program focused on understanding the chemical and biological processes that shape natural and engineered environments.

Established in 2008, the ACS Fellows Program honors a distinguished group of scientists who have made exceptional contributions to chemistry and related fields while also demonstrating dedicated service to the society. With this election, Tang joins 17 Georgia Tech ACS Fellows.

"I’m deeply honored," Tang said. "This recognition reflects the contributions of many outstanding students, postdoctoral researchers, colleagues, collaborators, and mentors throughout my career. I am grateful for the opportunity to work alongside such talented people to advance scientific discovery and build interdisciplinary partnerships that address critical energy and environmental challenges."

Founded in 1876, the American Chemical Society represents more than 170,000 members worldwide and is a leading source of scientific information through its journals, conferences, and educational programs.

The fierce backlash against data centers shows no sign of easing up.

Since early 2024, more than 1,200 public actions – including zoning fights, public campaigns and temporary moratoriums – have been logged by the Data Center Tracker, a public U.S. database of community responses to data center site selection. Among the concerns, grid capacity, water use and transparency around siting appear most often.

This momentum is leading to political action. In Maine, lawmakers passed a contested bill in spring 2026 that would have imposed the nation’s first statewide moratorium on new data centers. Gov. Janet Mills ultimately vetoed the measure on grounds that it would scuttle a US$550 million conversion of the closed Androscoggin Mill in the town of Jay into a data center.

But in a nod to the political climate, Mills said she supported in principle a pause in development and signed separate legislation barring state tax incentives going to data centers. She also pledged to create a council to study the industry statewide.

Maine’s dispute shows how statewide decisions on whether to promote or curb data centers can come down to one local case. It was no isolated example: Up to 10 other states are considering similar measures to contain their expansion.

But lawmakers across the country still lack clear evidence on whether new data centers can boost the economies of the communities hosting them.

As scholars of how technological change and innovation shape business strategy, we set out to produce rigorous research so that policymakers can make better decisions for their communities despite the emotions on both sides.

What we found was that data center development can boost growth and jobs – but these benefits are most pronounced when the local economy is more urban and developed. In fact, it turns out that the local economy around a data center matters more than the facility itself.

Testing the Data Center Promise

For years, state and local governments have courted data center projects with property tax abatements, sales tax exemptions and other incentives. Some jurisdictions still compete aggressively, but more and more are turning the other way, blocking tens of billions of dollars in proposed investments.

To understand the full economic impact, we combined records of when the centers began operating with data on local economic activity. We then compared how those economic outcomes changed before and after a county’s first data center opened relative to similar counties without data centers.

Overall, we found that data centers do boost growth. In the first three years after one opened, local employment rose on average by about 0.9%, wages by 1.1%, and the number of business establishments by 1%. Longer term, those effects grew to roughly 3.5%, 5% and 4.7%, respectively. Household income and building permits, meanwhile, increased by 1.9% and 16.1%, respectively. All of these gains accumulate gradually, rather than at once.

But the average effects mask an important pattern. Data centers are more likely to juice the economy when there’s a cluster of labor and capital already nearby, such as construction contractors, equipment suppliers, professional services and a skilled workforce.

In metropolitan counties, where that cluster of labor and capital is thicker, employment jumped by about 4.1%, while wages increased by 5.5%. In less populous counties, by contrast, job and wage spillovers were negligible. This suggests that the host community’s level of economic development matters more than the size of the project.

That said, other factors also affected local economic effects from one area to the next. Facilities operated by major tech companies, for example, raised local wages more than smaller companies. In addition, counties that attracted multiple data centers within five years of the first showed larger cumulative gains than counties with a single, isolated facility.

What About Electric Bills?

Electricity in the United States is delivered through complex regional grids and regulated utilities. In turn, retail prices depend on state and local rules and how costs are allocated among households, businesses and large industrial users.

This complicated patchwork goes to the heart of one of the biggest criticisms of data centers: Because they’re extraordinarily power-intensive, opponents say, they hike electric bills for consumers. So we looked at counties where a utility’s service area was localized enough to isolate the effects. We found that retail electricity prices rose by about 5% after a data center becomes operational.

Our estimate of 5% is not universal, however. Utility territories most often span multiple counties, while rate-setting rules differ by state and utility. And prices are affected by other factors, such as weather, transmission systems and regulations. That made the electricity effect harder for us to pin down than the other economic outcomes we studied.

But if our estimates stand, our figure is substantially lower than some more sensational reports, which may not be correct in attributing bigger hikes in electric bills to data centers.

Why Tensions are Running High

Pushback against data centers has picked up since 2024, as proposed projects have grown larger and more visible. Communities often make decisions amid uncertainty, with little local evidence to draw on.

Our findings help clarify part of that uncertainty: Economic spillovers are strong in metropolitan counties, while many rural counties see minimal gains in job growth.

We also find that opposition to data centers is more common where data centers already operate. That pattern suggests local experience may matter, although it doesn’t explain how much opposition reflects direct local experience versus broader anxiety about the impact of artificial intelligence more generally.

Beyond the Construction Incentives

As more data center siting decisions come up, lawmakers will need to judge whether a county’s economy will benefit and whether the project’s terms will help all residents even when they don’t share those gains. This means that the details of local subsidy design matter, including tax incentives, electricity tariff arrangements, grid and water upgrades, and whether any new resulting tax revenue will boost public services.

Together, those factors can matter more than the headline investment figure touted in a company press release. While our findings are a starting point to help navigate this emotional debate, more work is needed on how these other decisions shape community outcomes.

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

Researchers at Georgia Tech play a key role in the international collaboration. The Georgia Tech-LIGO research group includes School of Physics Professor Laura Cadonati, Assistant Professor Surabhi Sachdev, Research Scientist Margaret Millhouse, Postdoctoral Scholar Prathamesh Joshi, eight graduate students, and multiple undergraduates.

The LVK network detects gravitational waves when a massive cosmic event — like the collision of two black holes — creates invisible ripples in the fabric of space-time. Waves ripple out at the speed of light, and millions of years after the events that first created them, they reach the LVK detectors. 

But detecting gravitational waves does not simply mean capturing a signal — clues first need to be untangled from background noise.

“Identifying gravitational-wave signals requires carefully separating real astrophysical events from random fluctuations in the data,” says School of Physics graduate student Urja Shah, whose work to quickly identify phenomena supports rapid follow-up by the broader astronomical community.

To support the identification of phenomena, School of Physics graduate student Megan Arogeti conducts consistency tests between waveforms, checking results to find unexpected or unusual features. “Tests like this give us confidence in our models as we continue to observe gravitational waves with increasing sensitivity,” she explains. “They support new observations and help identify exciting new physics.”

“These efforts help ensure that gravitational-wave signals are robustly identified and accurately characterized, turning each detection into a precise measurement,” adds Shah. “In turn, these measurements deepen our understanding of some of the most massive and dense objects in the universe and the fundamental laws governing the cosmos.”

Astrocalibration Autotune

When a sensor detects a gravitational wave, it produces a distinctive response, says School of Physics graduate student Shobhit Ranjan. “Those signals encode a wealth of information we can analyze to learn about their sources — their masses, spins, distance, and location.” But in order to detect these chirps, the detectors must be carefully calibrated, and if calibration is not optimal, the signals can be compromised.

Now, a new tool is helping the LVK collaboration recalibrate less optimal signals. The technique is already showing promise: In an article recently accepted in Physical Review Letters, LVK researchers successfully applied it to two interesting signals. The first signal served as a testing opportunity for the method. The team used astrocalibration to recover the data and check it against secondary independent calibration data that was available. They then put the technique to use, recovering information from a second event where no secondary calibration data were available. 

“Like autotune in the music industry, the new research shows that theoretical models can be used as guides, similar to how sheet music can help a studio shift off-key music to its correct tone,” Ranjan explains. “These theoretical models suggest the shape of the signal, and together with data from other detectors, we can adjust the data and read it correctly.”

“The fact that these detectors can now not only sense cosmic events, but leverage them to improve the data being collected marks a new era in gravitational wave science,” he adds.

A Record-Setting Dataset

The LVK Collaboration also published their fifth catalog of gravitational wave events this spring. The findings include an updated estimate of how fast the universe is expanding, evidence for the existence of second-generation black holes, the most precise sky localization ever achieved for a gravitational wave source, and the first measurement of three vibrational modes of a black hole.

“Our group helped enable 140 detections out of the 161 reported in this catalog,” says Joshi, who contributed to one of the flagship searches and designed a specialized search focused on detecting especially heavy black hole mergers.

Joshi also worked on determining precise locations of where the gravitational waves originated from in the universe — research that he says will allow astronomers around the world to perform long-term follow-up observations of interesting events.

One record-setting detection showed two black holes that had violently collided more than 3 billion light-years from Earth. Researchers were able to pinpoint its location in the sky more precisely than any other gravitational wave event observed before.

Improvements in the LVK network’s ability to localize events along with the large number of detections allowed for a better estimate of the Hubble constant, which measures the rate at which the universe is expanding. The new measurement is over 25% more precise than previous estimates.

The new catalog also includes the “clearest” gravitational wave signal ever detected. The clarity of the signal led to the most accurate test of general relativity ever performed and confirmation of Stephen Hawking’s black hole area theorem.

“This catalog provides not just the largest number of black hole detections, it marks a new era of rapid progress,” Sachdev says. “This is just the beginning of what these observations will allow us to uncover.”

Artificial intelligence (AI) is changing far more than hospital paperwork. Researchers say it's beginning to help doctors make clinical decisions, identify mental health risks earlier, expand care through smartphones and wearable devices, and extend healthcare to people who might otherwise go without it. 

Caused by the Vibrio coralliilyticus pathogen, the infection is one of the most notorious causes of tissue loss and death in stony corals. In the study, all untreated corals bleached within 48 hours. But corals exposed to the predatory bacteria fared much better: more than half showed no signs of bleaching beyond the infection site — and disease progression was effectively halted. 

“Disease is a major driver of death for these corals, and with sea surface temperatures continuing to rise globally, we anticipate that rates of disease will only increase. It’s part of a deadly synergy profoundly threatening Caribbean coral reefs,” says lead author Lauren Speare, assistant professor in the School of Biological Sciences. “Predatory bacteria function like a living probiotic, fighting coral disease without harsh side effects. This could be a targeted way to protect and treat our most vulnerable coral reefs."

The study, “Halobacteriovorax Halts Disease Progression in Endangered Caribbean Corals,” was published in The ISME Journal. In addition to Speare, the research team included Georgia Tech master's student Chloe Manley and postdoctoral scholar Macey Coppinger; University of California, Santa Barbara graduate students Sunni Patton and Eddie Fuques, and Professor Rebecca Vega Thurber, director of the UCSB Marine Science Institute.

Natural Defenders

Speare became interested in the research while completing her postdoctoral training with Thurber. “Dr. Thurber discovered that predatory bacteria are present in many coral microbiomes,” Speare recalls. “We theorized that they might be contributing to what keeps the ecosystem healthy, balancing it through predation.” 

At the time, the theory was hard to test. Marine predatory bacteria are difficult to preserve long-term, making experiments challenging. The bacteria are also extremely scarce, with populations increasing during a coral infection and rapidly declining after. Catching them while their populations are high is a matter of timing, Speare says.

"It's a bit like trying to catch a mountain lion in the act of hunting a deer. If we aren’t looking at the right time, we might miss it entirely,” Speare says. “I knew that if I wanted to study these bacteria in more detail, I would need to carefully design my experiments and timing.”

Testing the Treatment

To test their theory, the team spent six weeks conducting experiments at the Mote’s Elizabeth Moore International Center for Coral Reef Research and Restoration (IC2R3) in Summerland Key, Florida, a facility that maintains lab-grown living corals in seawater aquariums.

“First, we had to make our corals sick,” Speare says. “But there wasn’t an established way to reliably create these infections in this species in a laboratory setting.”

After weeks of experimenting, Speare developed a “pathogen-sticker,” a small agar patch containing the disease-causing pathogens. When placed at the coral’s base, it mimics how infections spread in the wild.

Then, at the first sign of infection, the team treated the coral with the Halobacteriovorax predatory bacteria. “Surprisingly, the most effective method was to pour the bacteria directly into the sick coral’s tank,” Speare says. “The bacteria are tiny, so we were able to create a concentrated liquid of them by using a filter small enough that only they can pass through.”

Halobacteriovorax are among the fastest-known predatory bacteria, and quickly navigate to their food source – presumably the pathogen causing the infection.

From Aquariums to Oceans

Because of the straightforward delivery method, Speare believes the team’s methods could be readily adapted for coral restoration efforts, offering a simple way to deliver treatment on natural reefs.

“There are several approaches to treating corals and mitigating stress, but these techniques don’t work for all situations and all species,” she explains. “Corals are complex, and there is no single cure-all, so we need as many tools as possible to help corals survive.”

For Speare, the next step will be to move from lab-based work to reef environments.  She’s particularly curious as to why the predatory bacteria aren’t already moderating illness on natural reefs. “If this is such an effective way to control pathogens, why isn’t this system preventing disease outbreaks on reefs already?" she says. "We need to understand what's limiting this natural defense system – and that’s what we’re digging into next."

Funding: Lauren Speare was supported as a Simons Foundation Awardee of the Life Sciences Research Foundation. The Vega Thurber Lab was funded by the National Science Foundation.

DOI: https://doi.org/10.1093/ismejo/wraf270

One study found that admissions data offers limited insight into long-term academic success. The other challenges assumptions about so-called "lurkers," students who rarely post in online discussions but may still be deeply engaged in their courses. Together, the studies suggest that what matters most for student success may not be the easiest thing to measure.

Presented at the Learning@Scale conference in Seoul, South Korea, the research draws on data from Georgia Tech's Online Master of Science in Computer Science (OMSCS) program, one of the world's largest online degree programs. The program's scale gives researchers access to data from thousands of learners and allows them to identify patterns that would be difficult to detect in smaller educational settings.

Predicting Success

The long-term success study analyzed years of admissions and student performance data to examine whether application materials can predict what happens after a student applies. The research focused on three practical issues that can influence student success: who gets admitted, whether the admitted students matriculate, and who ultimately completes the program. OMSCS has always had a unique admissions model that focuses more on holistically evaluating a student’s background rather than GPAs or GRE scores and does not require applicants to have a strong computer science background or undergraduate education. 

"OMSCS has always followed a different admissions model from basically everyone else in higher education, so we can't draw from prevailing wisdom about what students to admit," said David Joyner, interim vice provost for AI in Education and executive director of online education and OMSCS. "Enough time has passed since we moved to a new admissions system that we finally could step back and look at what factors predicted success."

The researchers found that application materials could reasonably predict admissions and matriculation decisions. But when it came to forecasting retention and long-term success, early-course performance — not application information — played an outsized role in predicting whether students would remain in the program.

"I've always thought that success is most predicted by invisible factors like intended time commitment and external incentive to success," Joyner said. "But I thought there would be some signal in the application data. It's encouraging that there's not."

Learning About Lurking

Another indicator of student success is participation. It's often assumed that students who primarily read discussion forums rather than actively posting in them — sometimes called "lurkers" — are less engaged in their courses. Marjorie Ivy, lead author of the second study on lurkers and a 2025 OMSCS graduate, became interested in the topic through her own online learning experience.

"I've been that student in an online course who reads every discussion thread, thinks deeply about the material, feels genuinely connected to what's happening in the class — and never posts," Ivy said. "That mismatch between what activity logs say about a student and what the student is actually experiencing is what drew me to this topic. I wanted to see if we could give data and language to the quieter forms of engagement that often go unnoticed."

To better understand those students, the researchers looked beyond behavioral data and examined how learners perceived their social experiences in a course. Students completed surveys about belonging, peer interaction, and whether they felt their contributions were acknowledged. Using similarity algorithms and network analysis that examines relationships between different people, the researchers grouped students into clusters of learners who shared similar attitudes about their course experiences. The results revealed that some students who rarely posted still reported feeling connected to their classmates and learning community. 

Looking Beyond the Numbers

Although the studies examine different stages of the student journey, they arrive at a similar conclusion: Visible metrics often miss important parts of the learning experience. Understanding student success may require looking beyond what is easiest to count.

"My biggest hope is this program will signal to other universities how broken our traditional admissions model is," Joyner said. "We should be giving more students the chance to succeed, because higher education is not currently accommodating plenty who can succeed."

Veronica Rivera, an incoming assistant professor in Georgia Tech's School of Cybersecurity and Privacy (SCP), studies human-computer interaction, security, and privacy to create safer digital experiences. Her research earned her selection to the second cohort of the Computing Research Association (CRA) Trustworthy AI Research Fellowship for Early Career Scholars.

"I am excited and honored to be part of this year's CRA Trustworthy AI Research Fellowship cohort," said Rivera. 

"This program reflects the importance of cross-disciplinary research and collaboration in building AI systems that benefit and support society. I look forward to spending the next year building collaborations that support me and my students' research into protecting the digital safety of the diverse communities who use AI tools."

Rivera's research examines how technology shapes interpersonal relationships. Using empirical and design-based methods, she partners with communities affected by technology-facilitated abuse to understand digital safety risks and develop technologies that better protect users.

Through the fellowship, Rivera will study how AI is reshaping technology-facilitated abuse and develop data collection methods that enable researchers to assess these evolving risks over time.

"Trustworthy AI is a key research area in the School of Cybersecurity and Privacy and the College of Computing," said SCP Interim Chair Mustaque Ahamad. "The CRA Trustworthy AI Research Fellowship recognizes Veronica's innovative research and will help her build a research program that advances an area of strategic importance to our school and the broader AI community."

Supported by Microsoft, the CRA Trustworthy AI Research Fellowship recognizes early-career computing researchers who combine technical expertise with interdisciplinary approaches to address the ethical, societal, and human-centered challenges of artificial intelligence. The fellowship provides interdisciplinary training, mentorship, and collaboration opportunities that help researchers integrate ethical, societal, and human-centered perspectives into AI research and development.

Over the next year, Rivera and the other fellows will participate in a series of professional development activities, including a four-day Field School in Cambridge, Massachusetts. The program also includes quarterly virtual meetings, mentoring opportunities, and collaboration with scholars participating in related AI and data ethics programs.

DeMillo was among 80 computer scientists worldwide selected for the Academy's founding class and was the only Georgia Tech faculty member recognized.

"I am honored to be included in the inaugural class of the ACM SIGSOFT Software Engineering Academy," said DeMillo. "This recognition reflects the work of outstanding students, collaborators, and colleagues over many years. Software engineering research has transformed the way society builds and depends upon software, and I hope our community will continue to advance the scientific foundations needed to make software more reliable, secure, and worthy of the trust people place in it."

Established by ACM SIGSOFT, the Software Engineering Academy is a standing body of honor that recognizes members of the software engineering community whose lasting technical contributions, leadership, and service have shaped the field. The Academy celebrates researchers whose cumulative work and influence have advanced software engineering as both a scientific discipline and professional practice.

"Rich's research in software testing is recognized among the most influential contributions to the field of software engineering," said SCP Interim Chair Mustaque Ahamad. "His inclusion in the inaugural ACM SIGSOFT Software Engineering Academy demonstrates the lasting impact of his research on building more reliable software systems."

The inaugural class was selected from leaders whose contributions have already been widely recognized across the software engineering community, including ACM Fellows and recipients of ACM SIGSOFT's Outstanding Research Award. Beginning next year, new Academy members will be elected annually through a community nomination process.

DeMillo served as the founding chair of Georgia Tech's School of Cybersecurity and Privacy, the first school of its kind at a top research university. He previously served as the John P. Imlay Dean of the College of Computing and directed the Georgia Tech Information Security Center.

Throughout his career, DeMillo has held leadership positions across academia, industry, and government. He served as Hewlett-Packard's first chief technology officer, led computing research at Bell Communications Research, directed the Computer Research Division at the National Science Foundation, and led the Software Test and Evaluation Project in the Office of the Secretary of Defense.

His research spans software engineering, cybersecurity, election security, and the societal impacts of digital technology. His 1979 paper, Social Processes and Proofs of Theorems and Programs, is widely regarded as a foundational work in software engineering and has been recognized as one of the 50 most influential papers in computer science.

In addition to his research, DeMillo has helped shape higher education through the creation of Georgia Tech's Center for 21st Century Universities. He is a fellow of both the Association for Computing Machinery and the American Association for the Advancement of Science.

Read more »

Read more »

Their work, led by Sourabh Saha, associate professor and Woodruff Faculty Fellow, and Harnjoo Kim, who conducted the research during his doctoral studies and later as a postdoctoral fellow in Saha's lab, was recently published in the journal Nature Communications.

Nanoscale 3D printing allows researchers to create structures thousands of times smaller than the width of a human hair. These structures have potential applications in fields ranging from advanced computing and optics to biomedical devices and clean energy technologies. However, increasing printing speed often comes at the expense of quality.

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

• AI is accelerating cyberattacks.
• The same technology can strengthen defenses.
• The biggest risk is falling behind.

Artificial intelligence is changing cybersecurity on both sides of the battlefield. The technology helping organizations improve efficiency also enables cybercriminals to identify vulnerabilities, develop exploits, and launch attacks at unprecedented speed.

Researchers in the School of Cybersecurity and Privacy (SCP) say the greatest concern is not that AI is creating entirely new forms of cyberattacks. Instead, it is accelerating activities that attackers already perform, making existing threats quicker, cheaper, and harder to stop.

"AI is dramatically speeding up cyberattacks," said Brendan Saltaformaggio, associate professor in the SCP and the School of Electrical and Computer Engineering (ECE). "AI can identify vulnerabilities far faster than humans and often in places humans wouldn't think to look."

Hackers Are Moving Faster

Most cyberattacks include several stages: finding vulnerabilities, developing ways to exploit them, gaining access to systems, and pursuing a goal such as stealing information or disrupting operations. According to Frank Li, associate professor in the SCP and ECE, AI is having its biggest impact on the early phases of that process.

"AI can help attackers explore potential decisions and implement attacks faster than in the past, whether it's identifying software bugs or constructing social engineering hooks," Li said.

The pace of attacks has already changed dramatically. Peter Swire, J.Z. Liang Chair in the SCP and professor of law and ethics in the Scheller College of Business, says attackers are moving from vulnerability discovery to exploitation much faster than in the past.

"The average time until an exploit is detected even a couple of years ago was measured in months," Swire said. "Now it is measured in hours."

That compressed timeline is forcing organizations to rethink how quickly they identify, prioritize, and patch vulnerabilities.

The Risk Reaches Everyone

Healthcare systems, critical infrastructure providers, government agencies, and small businesses remain attractive targets because they often manage sensitive information or essential services while relying on legacy technology. But experts emphasize that no organization is immune.

"Unfortunately, everyone is at risk," Saltaformaggio said. "AI is not creating new victims; AI is making attackers faster and more effective at targeting the same organizations they have always pursued."

Organizations with outdated systems or limited cybersecurity resources face particular challenges because AI allows attackers to identify weaknesses in less time and at lower cost than ever before.

Fighting AI With AI

Cybersecurity defenders also have access to the same technology.

Experts say AI can strengthen defenses before, during, and after a cyberattack. Defenders can use AI to identify and patch vulnerabilities more quickly, reducing opportunities for attackers to gain access. AI can also detect subtle signs of intrusion by correlating activity across networks and recognizing patterns that would be difficult for humans to spot in real time.

Once an attack occurs, AI can support rapid investigation and response by analyzing how the compromise happened, identifying root causes, and helping deploy targeted protections.

"AI can help defenders in every step of stopping a cyberattack," Saltaformaggio said.

Researchers at Georgia Tech are already demonstrating AI's defensive potential. Saltaformaggio pointed to Georgia Tech's recent success in the Defense Advanced Research Projects Agency’s (DARPA) Artificial Intelligence Cyber Challenge, which highlighted how AI systems can autonomously discover and reason about software vulnerabilities at large scale. Swire also noted that a Georgia Tech team led by Professor Taesoo Kim won a $4 million DARPA prize for developing advanced AI-based cybersecurity defenses.

Speed Is the New Defense

Despite the promise of AI-powered security, significant challenges remain. Security teams need AI tools they can trust, ones that explain how they reached conclusions and provide evidence that analysts can verify. Attackers may also attempt to manipulate AI systems, creating new risks for organizations that rely heavily on automated tools.

Li says organizations cannot rely on traditional, human-paced security processes to keep up.

"AI's primary impact on cyberattacks is enhancing speed and scale," Li said. "Organizations need to adapt to more agile defenses and processes that account for this, in many cases relying on AI as well to help speed up defensive actions."

Organizations also need to rethink how they respond to vulnerabilities. Swire argues that traditional patch management is no longer fast enough in a world where exploits can emerge within hours.

"The entire process for patching systems will have to be re-engineered," he said.

The cybersecurity landscape has always been an arms race between attackers and defenders. AI hasn't changed that reality. It has simply accelerated it. The organizations that will be best positioned are those that adopt AI as quickly as the adversaries they are trying to stop.

The SCC is home to seven student engineering competition teams and provides workspace, tools, and resources to help students apply classroom learning to real-world engineering challenges.

In his new role, Simmons will provide strategic leadership and operational oversight for student competition teams, facilities, staff, budgets, sponsorships, and safety programs. He also will teach and mentor students through engineering design and experiential learning courses, helping connect classroom instruction with project-based experiences.

“Richard brings a unique combination of industry experience, research leadership, and deep commitment to student success,” said Carolyn Seepersad, Eugene C. Gwaltney, Jr. School Chair. “As an accomplished engineer and a Georgia Tech alumnus, he understands the value of experiential learning and is well-positioned to lead the Student Competition Center.”

Simmons, ME 1993, joined Georgia Tech in 2016 after spending the first 20 years of his career leading research, technology, and business development initiatives in the automotive industry, energy sector, and federal government. After graduating from Tech, he earned his master’s and doctoral degrees from Purdue University and later became a licensed professional engineer.

Over the past decade, Simmons has held several leadership and research positions within Georgia Tech’s Strategic Energy Institute, including founding director of the Energy Policy and Innovation Center and, most recently, director of Research and Studies. He has also taught a variety of courses at the Woodruff School, including ME 2110, Capstone Design, Energy Systems, and Renewable Energy.

Read Full Story on the ME News Page

Blending engineering challenges, field experiences, and team-based design projects, the weeklong program in June gave students a dynamic introduction to energy, sustainability, and engineering innovation and a rare opportunity to engage directly with the technologies, infrastructure, people, and ideas that help power the world.

“Our goal is to get outside of the classroom, have fun, and demonstrate how a STEM education can literally help turn on lightbulbs,” said SEI’s director of Research and Studies, Rich Simmons, who also directs Energy Unplugged. “Through hands-on learning, field trips, and real-world experiences, these creative students are learning that everyone can play a role in our energy future. Along the way, they are gaining a deeper understanding of the tradeoffs and challenges engineers face and learning from experts about pathways to an energy career.”

Mousetrap-Powered Cars
Putting those ideas into practice from day one, the camp began with an engineering challenge in which students designed and constructed mousetrap-powered cars. Using the stored potential energy of a mousetrap spring to propel their vehicles, participants explored how energy is converted from one form to another and identified sources of friction and inefficiency that affect the distance traveled. The activity encouraged students to think like engineers, iteratively testing and refining their designs to improve results.

Engineering Optimization and Tradeoffs
Similar problem-solving skills were put to the test during an RC car optimization challenge. Equipped with a battery-powered vehicle and energy-monitoring systems, students were tasked with completing a driving course while maximizing their score by balancing speed, energy consumption, safety, and cargo capacity. Participants had the option to add weights and tennis balls to increase potential points, but doing so increased the risk of penalties from dropped cargo, missed obstacles, or vehicle rollovers. The exercise highlighted the tradeoffs engineers routinely face when optimizing systems under competing constraints.

“The overall interest in green energy among youth is increasing, so having demonstrations and experiments as well as some high-level lectures on the actual science was a great way to engage the students,” said student assistant William Nudd, a senior in mechanical engineering who assisted with the camp. “When I was in their shoes, I had never attended a physics class, so the camp was definitely getting them a step ahead and did a great job introducing and showcasing key concepts related to energy: How does my home get electricity? Where does energy come from? How do power plants operate?”

Trivia, Demos, and Scavenger Hunts
Additional activities throughout the week included energy-themed trivia competitions, a steam engine demonstration, a solar microgrid exercise, and a campus scavenger hunt. Together, they reinforced classroom concepts through interactive learning and encouraged students to connect technical principles with practical applications.

Field Trips to Power Plants
While these activities taught foundational concepts, a highlight of the camp was a series of field trips that allowed students to observe large-scale energy infrastructure in operation. Participants toured the Georgia Power McDonough-Atkinson Plant, where they learned how combined-cycle power plants generate electricity using both gas and steam turbines to improve efficiency. Students also visited the Morgan Falls hydroelectric facility, getting an up-close view of the massive generators and equipment used to convert the energy of flowing water into electricity.

Campus Tours
In addition to exploring regional energy infrastructure, students were introduced to Georgia Tech’s innovation ecosystem through visits to campus makerspaces and research facilities, including the Flowers Invention Studio and The Kendeda Building for Innovative Sustainable Design. Students explored one of the nation’s most advanced examples of sustainable building design during a guided tour of The Kendeda Building, which generates 200% of the energy it consumes. Here they learned how energy efficiency, renewable generation, and resource conservation can be integrated into the built environment.

Final Projects 
To bring together the concepts explored throughout the week, students worked in teams on a final design challenge centered around a solar-powered disaster relief trailer on loan from the Footprint Project. Equipped with photovoltaic panels and battery storage, the trailer was originally designed to provide off-grid power during emergencies. Students were challenged to identify additional uses for the system during periods when disaster response was not required. Many teams proposed sustainable food truck businesses powered by the trailer’s solar energy system.

Teams also evaluated cooking technologies such as pressure cookers and slow cookers, comparing energy consumption, power requirements, efficiency, and operating costs. Students examined how energy demand aligned with available solar generation and battery storage while conducting economic analyses to determine business viability and profitability. The project integrated engineering, economics, and sustainability principles while encouraging creative thinking and collaborative problem-solving. 

“Energy Unplugged is an inspiring demonstration of how hands-on engineering experiences can spark curiosity and passion in the next generation of STEM leaders,” said student assistant Alvaro Hucker, a senior mechanical engineering student. “Working with this group and seeing the fun they were having brought back fond memories of my own childhood. It was an amazing experience.”

Student Contributors: Alvaro Hucker, Senior, Mechanical Engineering and William Nudd, Senior, Mechanical Engineering.

Georgia’s $41 billion forest products industry needs a transformation, and a Georgia Tech research team is reimagining how pulp mills use energy and what they can make from their byproduct streams. 

Researchers at Georgia Tech say they have developed a system to help answer that question.

Known as FIRA, the tool analyzes drone crashes to determine whether they were caused by tampered machine-learning (ML) models. The team will present its findings at the 35th USENIX Security Symposium in August. 

The research addresses a growing safety challenge as drones are increasingly used for deliveries, infrastructure inspections, and agriculture.

As drones rely more on machine learning to navigate and make decisions, they also become vulnerable to model poisoning attacks. In these attacks, adversaries manipulate an AI system during its learning phase, embedding hidden triggers that can cause failures under specific conditions.

“Machine learning drones are making more decisions in flight, which makes ML a safety-critical component of these systems,” said Yizhi Huang, Ph.D. student and lead researcher on the project. 

“When something goes wrong, investigators need a way to ask whether the model was responsible, but the model is the part of the system that no one can examine after a crash. FIRA gives investigators a way to investigate these cases by reconstructing what the model was doing during the crash. As more drones run with ML, this kind of forensic capability can help drones be used more effectively and safely.”

When a drone crashes, investigators must determine whether the cause was malicious interference, weather, or mechanical failure. Without reliable forensic tools, accountability is difficult to establish, and safety standards are harder to enforce.

FIRA identifies how drone components interact with machine learning models and monitors those interactions in real time, even with limited bandwidth.

The system functions like a flight recorder, capturing key system activity and reconstructing a timeline after a crash. It then analyzes the model’s behavior to determine whether a malicious trigger was introduced via poisoned ML training data.

In tests across multiple drone platforms and crash scenarios, FIRA identified failure causes and distinguished cyberattacks from environmental or mechanical issues.

The system does not require access to a drone’s source code, making it practical for real-world investigations.

“As commercial drone use expands, tools like FIRA could help improve accountability and trust in AI-powered systems operating in public airspace,” said Huang. 

FIRA: Enabling Automatic Forensic Investigation of Unmanned Aerial Vehicles was led by Georgia Tech’s Cyber Forensics Innovation Lab in cooperation with the Cyber-Physical Security Lab. These labs reside in the School of Cybersecurity and Privacy and the School of Electrical and Computing Engineering. 

The surrounding trees resemble those of a eucalyptus forest, which could indicate northern Portugal or the Spanish region of Galicia.

It’s the signposts on the road that give it away. They are flat and wide, which is common in Spain but not in Portugal.

Casapu, a master’s student in Georgia Tech’s School of City and Regional Planning, correctly reasons that the picture of a road he’s looking at is in Galicia.

Give Casapu a photo, and he will likely be able to tell you where it was taken. 

“I start with infrastructure clues that are specific to a country, region, state or province,” Casapu said. “They include roads or electricity poles, which often remain consistent throughout a country. Once you narrow down the country, you can use more specific factors like vegetation, specific landscapes, or architecture, because these are very nuanced. It’s a top-down approach.”

This is why Casapu is the reigning GeoGussr World Champion — and the ideal expert to test vision-language models (VLMs) on how good they are at geolocation.

GeoGuessr is a geography browser game launched in 2013 that invites players to guess the location of random Google Street View images. Casapu was already known as one of the top players in the world before he won the third annual GeoGussr World Championship in September.

At the beginning of the spring 2025 semester, School of Interactive Computing professor James Hays reached out to Casapu and invited him to collaborate on a new project. Hays was looking to create a dataset to evaluate VLMs' geolocation ability and reasoning. 

“VLMs are surprisingly good at geolocation right out of the box, even when they’re not trained to be good at it,” Hays said.

Hays and his colleagues, associate professors Alan Ritter and Wei Xu, took issue with many AI companies claiming that the VLMs they were releasing were not good at geolocation.

“When Open AI released GPT 4 Vision, there were privacy concerns about the model’s ability to geolocate someone based on photos they’ve shared on the internet,” Ritter said. “Open AI said this wasn’t a concern and claimed the model wasn’t good at geolocation beyond being able to recognize a city or famous monument. We found that wasn’t the case. These VLMs are state-of-the-art at image geolocation tasks.”

Show Your Work

Hays and Ritter enlisted a team of some of the world’s top geolocators. It consisted of Casapu, Joshua Diao, a master’s student in computer science, and Tejas Santanam, a Ph.D. student in industrial engineering. They each received 500 images to geolocate.

Team members recorded their reasons for each of their answers. The result was GeoRC, the first benchmark for VLM geolocation performance, consisting of 800 “ground truth” reasoning chains. 

Hays and Ritter gave the same images to GPT 5, Gemini, Llama, and Qwen. The highest-performing model geolocated with 90% accuracy — not far off from the team’s 96% score.

However, a major distinction showed up in the reasoning chains. While Casapu and Diao provided clear explanations for how they deduce each location, the VLMs either couldn’t provide reasoning for their guesses or were vague in their answers.

“The research community has been demanding explanations from these models,” Hays said. “For example, how do they know the location is in Italy?”

Hays has been researching this subject for almost 20 years. As a Ph.D. student at Carnegie Mellon University in 2008, he was the first researcher to take a machine learning approach to geolocation. He introduced a new algorithm that could estimate a geographic location from a single image.

“When experts have audited these reasoning chains, we’ve noted many suspicious or hallucinated attributes,” he said. “When they hallucinate a geographic property, why is it so often consistent with the correct guess?

“I believe they’re not revealing the true reasoning pathway that they used to determine the image was Italy. They’re just implicitly recognizing that it was Italy for many reasons, then hunting for evidence to support that. Some of the things they say are true and supported by the image, and some are fabrications.”

Practice Partner

Casapu said there may be only a handful of GeoGuessr players who can currently outperform some top-tier VLMs in geolocation, and it may not be long before no one can.

“I think it could be more difficult playing against these models than playing against another human because a human has the possibility of making mistakes at the top level,” Casapu said. “If a well-trained model has that level of consistency, that is far beyond a normal person, and it would be much more difficult to beat.”

He added that working with Hays and competing against a machine improved his skill level and provided valuable practice ahead of the world championship. 

“It helps to take a step back and see why you’re making the guesses that you are,” he said. “Since then, I’ve taken a more methodical approach to how I practice. Writing these things down is a great way to see what you know and see why you make the guesses that you do. It’s been a great training tool.”

Casapu will defend his title at the 2026 GeoGussr World Championship in September.

Hays, Ritter, Xu, Casapu, Diao, and Santanm are all co-authors of a paper on GeoRC along with lead author Mohit Talrej and Ph.D. students Ethan Mendes and Jim Thannikary. The paper will be presented next week at the 64th Annual Meeting of the Association for Computational Linguistics (ACL) in San Diego.