Modern artificial intelligence (AI) platforms can summarize reports, analyze documents, and answer questions in seconds. But when information is spread across dozens of slides, charts, and tables, even advanced models can miss important details. 

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.”

News Contact

A School of Computing Instruction (SCI) faculty member recently shared his expertise in computing education with to an international audience.

SCI Instructor Pedro Guillermo Feijóo-García was selected by Fulbright Colombia to moderate the closing panel of the Fulbright Reimagined Summit 2026: AI Horizons: Learning Pathways for Tomorrow.

Held last month at Universidad del Norte in Barranquilla, Colombia, the summit convened scholars, educators, policymakers, and industry leaders to examine how artificial intelligence (AI) is transforming education, work, governance, and society.

Fulbright Colombia invited Feijóo-García to moderate the closing discussion, From Adopters to Architects: Professions of Tomorrow, in recognition of his research on human-AI interaction and the hidden curriculum in engineering and computer science education.

"As a Fulbright alumnus, being invited to contribute to such an important event was an honor and a privilege," Feijóo-García said. "Beyond the personal recognition, I viewed this opportunity as a meaningful platform to facilitate conversations around the future of education, technology, and workforce development."

From Computing Education to AI Futures

At Georgia Tech, Feijóo-García directs the People-Agents Research for Computing Education (PARCE) Laboratory. His research examines the intersection of computing education, STEM learning, and AI, focusing on student preparedness, professional development, and the hidden curriculum- which he explains as the implicit skills and expectations that shape students' academic and career success. 

Feijóo-García says his perspective is shaped by years of work in computing education. During his master's studies in systems and computing engineering at Universidad de los Andes in Colombia, he explored ways to expand access to computing education through interactive programming environments. He went on to earn his Ph.D. in human-centered computing from the University of Florida, where he focused his research on computing education and human-centered AI.

"AI is transforming how we learn, work, communicate, make decisions, and interact with one another," Feijóo-García said. "As educators, we need to prepare students not only with technical competencies, but also with critical thinking, ethical reasoning, collaboration, and the ability to adapt."

Preparing Students for the Professions of Tomorrow

Rather than viewing AI as a challenge for higher education, Feijóo-García sees it as an opportunity for universities to rethink how they prepare students for an evolving workforce. He believes educators should help students develop the judgment to know when AI can enhance their work and when independent reasoning and human expertise are essential.

"The conversation should not revolve around whether AI belongs in education, but rather how we integrate it responsibly and intentionally," Feijóo-García said.

He also hopes students begin to think of AI not only as artificial intelligence, but as augmented intelligence. "The goal should not be to replace human thinking, but to enhance it," he said.

Feijóo-García emphasized that AI should augment human capabilities rather than replace human judgment. Preparing students for an AI-driven workforce requires helping them understand when AI can support their work and when human reasoning, creativity, and expertise are essential.

Strengthening U.S.–Colombia Collaboration

The summit reinforced the value of collaboration among scholars, educators, policymakers, and industry leaders in advancing research and education. Earlier this year, Feijóo-García participated in another Fulbright Colombia event focused on strengthening scientific collaboration between Colombia and the United States.

The Fulbright Program, which operates in more than 160 countries worldwide, is the United States government’s flagship international academic exchange program to support peaceful relations between the people of the U.S. and the people of other countries. Fulbright Colombia, the binational commission for educational exchange between the U.S. and Colombia, has supported academic and scientific collaboration between the two countries since 1957.

Feijóo-García’s academic journey reflects the impact of these collaborations. The Fulbright Program supported his doctoral studies in the United States, and he continues to build connections between Colombia and the U.S. through his work at Georgia Tech.

"Scientific diplomacy is built on people," Feijóo-García said. "Events like the Fulbright Reimagined Summit provide the environment where trust is established, ideas are exchanged, and collaborations begin."

The Institute for Data Engineering and Science (IDEaS) has selected faculty to serve in two associate director roles that will center on developing internal and external community projects at the intersection of data sciences, machine learning, and AI. They will support the executive director, David Sherrill, in creating research and upskilling opportunities for the campus community in fundamental and applied machine learning and AI for research and by identifying promising new research collaborations and potential funding sources.

Ghassan AlRegib will serve as associate director for Research and Education, seeking large-scale funding opportunities, creating upskilling workshops, coordinating efforts with relevant student groups, and fostering thought leadership in areas relevant to IDEaS’ mission: data science, machine learning, artificial intelligence, and high-performance computing.

AlRegib is the John and Marilu McCarty Chair in the School of Electrical and Computer Engineering. His group, the Omni Lab for Intelligent Visual Engineering and Science (OLIVES), conducts machine learning research aimed at shifting learning systems from data-centric to human-centric, with an emphasis on robustness, uncertainty, human-AI interaction, and explainability. His team’s research is applied to vision, subsurface imaging, autonomous systems, healthcare intelligence, and education. 

Vijay  Ganesh has been appointed associate director for Research, after serving in this role on an interim basis since 2025. He will support the development of new strategic research initiatives, work closely with faculty, research staff, and industry partners to create and strengthen interdisciplinary teams, and help IDEaS seek large-scale funding opportunities.

Ganesh is a professor of computer science, and he served as co-director of the AI Institute at the University of Waterloo before moving to Georgia Tech in 2023. He is a co-founder and a steering committee member of the Centre for Mathematical AI at the Fields Institute and an AI Fellow at the Balsillie School of International Affairs. 

“I’m delighted that Vijay Ganesh has agreed to continue in the role of associate director of Research; his expertise in AI and formal verification methods has been central to our formulation of new research initiatives,” said Sherrill. “I’m also thrilled that Ghassan AlRegib is joining our leadership team. He is a longtime key IDEaS faculty member, and he has led multiple centers at Georgia Tech. His recent experience hosting a planning grant for his Accessible Healthcare Through AI-Augmented Decisions perfectly positions him to help lead IDEaS’ AI for Health initiative, and his experience in developing AI courses and educational tools makes him the right person to lead our AI upskilling workshops.”  

“I am thrilled to join IDEaS,” AlRegib said. “Data science, machine learning, and AI are no longer specialized disciplines; they are foundational tools on which nearly every research enterprise on campus depends. IDEaS' greatest value is not to be the place where AI happens, but to be the connective tissue that makes AI impactful and accessible for everyone else. This is the kind of work I care deeply about, helping connect faculty curiosity with collaborative teams, emerging methods with usable skills, and student interest with real AI capability. The best measure of our success will be what every other unit at Georgia Tech is able to accomplish because IDEaS exists.”

"I am delighted and honored to be reappointed as IDEaS' associate director for Research. AI is a paradigm-shifting technology that is transforming research across every discipline, and IDEaS is at the forefront of enabling that transformation at Georgia Tech,” Ganesh said. “My vision for this role centers on advancing the research on campus in both the foundations of AI and its applications to mathematics, science, and engineering. To that end, I look forward to shaping strategic research initiatives, partnering with faculty across campus to pursue large-scale funding opportunities, and organizing timely workshops and seminars that bring our community together. It is a privilege to continue this work.

-Christa M. Ernst | Research Communication Manager

At a time when medicine, energy, artificial intelligence, and national security increasingly depend on computing, the world looks to Georgia Tech’s newest graduates for answers to life’s most pressing challenges.

That sense of purpose shaped Spring 2026 Commencement, where School of Computational Science and Engineering (CSE) graduates celebrated years of research, collaboration, and discovery.

“Today, we celebrate you, your accomplishments, and your potential,” said Georgia Tech President Ángel Cabrera in his commencement address to Ph.D. graduates.

“I thank you for choosing a career of science and research when some question science and research. We need you to continue on this path. The world needs you.”

In addition to administering its flagship CSE Ph.D. and M.S. programs, the School of CSE offers doctoral degrees in computer science and machine learning. Ph.D. students who received their diplomas and doctoral hoods on May 7 at McCamish Pavilion were:

• Muhammed Balin (Ph.D. CS-CSE 2026), advised by School of CSE Professor Ümit Çatalyürek
• Andrew Hornback (Ph.D. CS-CSE 2026), co-advised by School of CSE Assistant Professor Yunan Luo and Wallace H. Coulter Department of Biomedical Engineering Professor May Wang
• Chengrui Li (Ph.D. CSE-CSE 2026), advised by School of CSE Assistant Professor Anqi Wu
• Xinhai Pan (Ph.D. CSE-CSE 2026), advised by School of CSE Assistant Professor Anqi Wu
• Kaan Sancak (Ph.D. CSE-CSE 2026), advised by School of CSE Professor Ümit Çatalyürek
• Agam Shah (Ph.D. ML-CSE 2026), co-advised by Scheller College of Business Professor Sudheer Chava and School of CSE Associate Professor Chao Zhang
• Kartik Sharma (Ph.D. CS-CSE 2026), advised by School of CSE Assistant Professor Srijan Kumar

This semester, 14 CSE doctoral students completed M.S. degrees and will continue their studies at Georgia Tech. They are: 

• Bin Bai (M.S. EAS-CSE), advised by School of Earth and Atmospheric Sciences Assistant Professor Pengfei Liu
• Afrouz Delshad (M.S. CSE-CSE 2026), advised by College of Computing Associate Dean for Graduate Education and School of CSE Associate Professor Elizabeth Cherry
• Roy Makkar Gabriel (M.S. ECE-CSE 2026), advised by School of Electrical and Computer Engineering Professor Ali Adibi
• Alina Maximovna Gorbunova (M.S. ISYE-CSE 2026), co-advised by H. Milton Stewart School of Industrial and Systems Engineering Professors Kamran Paynabar and Jianjun Shi
• Wenbo Hao (M.S. MATH-CSE 2026), advised by School of CSE Assistant Professor Peng Chen
• Xueyu Hu (M.S. MSE-CSE 2026), advised by School of Materials Science and Engineering Regents’ Professor Meilin Liu
• Dayoung Kang (M.S. AE-CSE 2026), advised by Daniel Guggenheim School of Aerospace Engineering and School of CSE joint Assistant Professor Elizabeth Qian
• Soohwan Kim (M.S. ME-CSE 2026), advised by George W. Woodruff School of Mechanical Engineering Professor David Hu
• Xuanang Li (M.S. MATH-CSE 2026), advised by School of Mathematics Assistant Professor Tom Kelly
• Nitya Maruthuvakudi Venkatram (M.S. AE-CSE 2026), advised by School of AE Regents’ Professor Dimitri Mavris
• Nilavrah Sensarma (M.S. BIO-CSE 2026), advised by School of Biological Sciences Professor John McDonald
• Benjamin Wilfong (M.S. CSE-CSE 2026), advised by School of CSE Assistant Professor Spencer Bryngelson
• Xiaofeng (Alex) Wu (M.S. CEE-CSE 2026), advised by School of Civil and Environmental Engineering Regents’ Entrepreneur David Frost
• Keyang (Alfred) Zhong (M.S. ISYE-CSE 2026), advised by School of ISyE Professor Chelsea White

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

Georgia Tech celebrated master’s graduates at a May 9 ceremony at Bobby Dodd Stadium. After the Institute celebration, graduates were recognized during ceremonies held by their respective colleges.

Mohammed Wazir Adain (M.S. CSE 2026)

Aditi Agarwal (M.S. CSE 2026)

Sudarshan Anand (M.S. CSE 2026)

Arjun Bansal (M.S. CSE 2026)

Shraddha Bharadwaj (M.S. CSE 2026)

Aarushi Biswas (M.S. CSE 2026)

Anurita Bose (M.S. CSE 2026)

Hao-Cheng Chang (M.S. CSE 2026)

Nai-Jen Cheng (M.S. CSE 2026)

Yida Cheng (M.S. CSE 2026)

Denys Chernenko (M.S. CSE 2026)

Aarushi Vishal Dhanuka (M.S. CSE 2026)

MacKenzie Taylor Starr Drury (M.S. CSE 2026)

Chandra Sekhar Reddy Edula (M.S. CSE 2026)

Shiqi Fan (M.S. CSE 2026)

Yuanting Fan (M.S. CSE 2026)

Wen (Ava) Feng (M.S. CSE 2026)

Amrutha Praveen Ganapathiyat Othayoth (M.S. CSE 2026)

Aman Garg (M.S. CSE 2026)

Xin Guan (M.S. CSE 2026)

Yunmei Guan (M.S. CSE 2026)

Srihas Gunda (M.S. CSE 2026)

Yihui Han (M.S. CSE 2026)

Keenan Wai-sean Hom (M.S. CSE 2026)

Shiqi Hu (M.S. CSE 2026)

Wenxin Jiang (M.S. CSE 2026)

Harneet Singh Khanuja (M.S. CSE 2026)

Hyunjeong Kim (M.S. CSE 2026)

Vijay Prabhas Kodamalla (M.S. CSE 2026)

Neel Kothari (M.S. CSE 2026)

Ziji Li (M.S. CSE 2026)

Qinye Liu (M.S. CSE 2026)

Ruixin Liu (M.S. CSE 2026)

Yibo Liu (M.S. CSE 2026)

Shenyifan Lu (M.S. CSE 2026)

Wenliya Lyu (M.S. CSE 2026)

Aditya Akash Mavle (M.S. CSE 2026)

Samuel Wesley Moss (M.S. CSE 2026)

Shruti Santosh Murarka (M.S. CSE 2026)

Karthic Palaniappan (M.S. CSE 2026)

Shrey P. Patel (M.S. CSE 2026)

Tanish R. Patwa (M.S. CSE 2026)

Tim Minh Phan (M.S. CSE 2026)

Jing Qi (M.S. CSE 2026)

Wanrong Qi (M.S. CSE 2026)

Hui Qiao (M.S. CSE 2026)

Aditya Raghavan (M.S. CSE 2026)

Araceli Rodriguez Vallejo (M.S. CSE 2026)

Chloé Saleh (M.S. CSE 2026)

Vanshika Shah (M.S. CSE 2026)

Kaichen Shen (M.S. CSE 2026)

Bohan Shu (M.S. CSE 2026)

Kunhao Song (M.S. CSE 2026)

Ajeet Karthik Subramanian (M.S. CSE 2026)

Jingyun Sun (M.S. CSE 2026)

Yupeng Tang (M.S. CSE 2026)

Michael Kenneth Thompson (M.S. CSE 2026)

Yu Chu Tsai (M.S. CSE 2026)

Viren Dipin Varma (M.S. CSE 2026)

Aarushi Chetan Wagh (M.S. CSE 2026)

Yiling Wu (M.S. CSE 2026)

Yitong Wu (M.S. CSE 2026)

Jiayi Xu (M.S. CSE 2026)

Shuyan Yang (M.S. CSE 2026)

Yiming Ye (M.S. CSE 2026)

Zhenghao You (M.S. CSE 2026)

Yijia Zeng (M.S. CSE 2026)

Jinkai Zhan (M.S. CSE 2026)

Yuehan Zhang (M.S. CSE 2026)

Xinyu Zhao (M.S. CSE 2026)

Yuqian Zheng (M.S. CSE 2026)

Alexander Zhou de Magalhaes (M.S. CSE 2026)

Shizhuo Zhu (M.S. CSE 2026)

Xiaoai Zhu (M.S. CSE 2026)

Xinjie Zhu (M.S. CSE 2026)

News Contact

When Chengrui Li walks across the stage this Thursday at Commencement, it will be his final, and perhaps easiest, performance at Georgia Tech. 

Between orchestra concerts, magic shows, and yo-yo exhibitions, Li thrives in the limelight. In fact, not much rattles his nerves considering the five years of pressure he endured studying computational neuroscience at Tech.

Before he returns to New York City to continue building brain-interface technologies at Meta, we caught up with Li to learn how he keeps such a cool head at Georgia Tech and beyond.   

Graduate: Chengrui Li

Research Interests: Computational neuroscience, eye-tracking experiments and data analysis, statistical machine learning

Education: Ph.D. in Computational Science and Engineering (CSE)

Faculty Advisor: School of CSE Assistant Professor Anqi Wu

What persuaded you to attend graduate school at Georgia Tech?

My undergraduate was at Sichuan University in China. We knew that the most cutting-edge technology and research were in the United States, so I participated in an undergraduate exchange program at the University of Tennessee, Knoxville, during my third year. 

I wanted to pursue a Ph.D. in neuroscience while also becoming very proficient in math and computer science (CS). This led me to apply to the CSE Ph.D. program over others. Georgia Tech’s CS ranking is very high, and the CSE program is very interdisciplinary, which matched my expectations super well. I did attain a solid education in math and CS at Georgia Tech. I also advanced my interest in neuroscience and its application by studying mathematical models and algorithms.

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

My variational importance sampling paper is a favorite. That one was based heavily on statistical inference. I spent many hours working through complicated derivation calculations, often half-awake and half-asleep after several late nights. 

This paper confirmed to me, though, that innovative research requires both hard work and inspiration, and that this endeavor can be rewarding. The paper was selected as a top 5% spotlight paper at ICLR 2024, a world-leading conference on artificial intelligence research.

Could you share more about your role as a research scientist at Meta?

I have been working on Meta’s electromyography (EMG) neural band. This next-generation human-computer interaction device connects with and navigates Meta’s AI glasses.

With the neural band, you can use finger gestures to control the display content you see through the glasses, like swiping your thumb to scroll the screen, or writing on your lap as if you had a pen in your hand to send WhatsApp messages.

How did your Georgia Tech education prepare you for this role?

By pursuing my Ph.D., I am more proficient in critical thinking, math, coding, and presentation. During my interview, I demonstrated these skills and provided my publication records. This helped me land an internship, enabled my success in that role, and led to a full-time position. Additionally, my background in computational neuroscience best matched the work on the EMG neural band team at a big tech company.

What advice would you give someone interested in graduate school?

First, be clear whether a bachelor’s or master’s degree meets your work needs, or if you are truly interested in a scientific research topic. This interest should be based on your own passion, not the current trends. Interest is an important factor in deciding to pursue a Ph.D. because you have to like the topic and like it for a long time. A Ph.D. will require you to dive deep into a subject you must be genuinely curious about.

Second, we are in a new era with rapid advances in information technology. Time is an invaluable resource and is shaped by technology. You have to think more about your time, consider where and how you spend it, and embrace ways to use it more efficiently. 

Can you tell us more about your hobbies and how you keep up with them?

I started learning violin when I was five years old, and magic tricks when I was 11. The brain is a supercomputer suitable for functional computation. Our brain is an interface between the objective and subjective, where computation plays a core role in integrating these exact mechanics into interpretations of the world. This realization was one of the important factors that inspired me to pursue my Ph.D. research in computational neuroscience.

Another comparison I’ve learned after playing violin for 23 years is that the cochlea in our inner ear is a fast Fourier Transformer that simultaneously computes the aesthetic of music for us. Performing magic tricks for 17 years taught me that all the occurrences of seemingly low-probability magic phenomena are achieved by either letting it be a certain event or exhausting all possibilities.

I also have other hobbies, like yo-yo balls. I enjoy performing all these skills in front of audiences. Performing brings me satisfaction when I see excitement and happiness from the people I entertain. I am very grateful to my parents for their cultivation and encouragement in doing things that bring me fulfillment. They taught me to be curious and explore my interests, to enjoy pastimes, and instilled the habit to not give up my passions. These were not secondary things that distracted me from coursework or Ph.D. research, but rather complementary parts of my life that bring out the best in me.

What is your favorite Georgia Tech memory?

I have a lot. For my research, I debated frequently with Anqi Wu, my advisor. These often went late into the night to defend my stances. These challenged my beliefs and made me a stronger scholar, for which I am grateful to Anqi for her time and patience.  

I also enjoyed performing in the Georgia Tech symphony orchestra with our great conductor, Chaowen Ting. I was involved with the Georgia Tech Chinese Students and Scholars Association, where I showcased magic and yo-yo performances at organization events.

News Contact

While people use search engines, chatbots, and generative artificial intelligence tools every day, most don’t know how they work. This sets unrealistic expectations for AI and leads to misuse. It also slows progress toward building new AI applications. 

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

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

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

[Related: GT @ CHI 2026]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

News Contact

The in-state rivalry between the Yellow Jackets and the Bulldogs usually heats up when Georgia Tech visits the University of Georgia. However, one Saturday last month, the focus shifted from competition to collaboration. 

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

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

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

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

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

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

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

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

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

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

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

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

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

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

Georgia Tech students who presented posters included:

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

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

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

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

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

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

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

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

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

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

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

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

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

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

News Contact

Georgia Tech researchers applied their expertise to a national research program that will shape the future of computing. Their work may yield more energy-efficient computers and better predictions for environmental challenges like carbon storage, tsunamis, wildfires, and sustainable energy. 

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

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

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

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

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

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

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

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

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

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

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

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

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

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

News Contact

The future of clean energy depends on algorithms as much as it does atoms.

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

Itamar Kimchi, assistant professor, School of Physics

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

Wenjing Lao, associate professor, School of Mathematics

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

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

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

News Contact

While not as highlight-reel worthy as the Winter Olympics and the World Cup, experts expect high-performance computing (HPC) to have an even bigger impact on daily life in 2026.

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

News Contact