Berlin is a growing Tech Hub in Europe, home to innovative companies and research institutions, and host to tech meetups, hackathons, and conferences. With focus on entrepreneurship and start-up culture, this program is a great option if you are a CM major, if your CS Threads are Intelligence or Information-Internetworks, or if you’re doing the Create-X: Idea-To-Protype Junior Design option.

Review the attached flyer and email berlin@cc.gatech.edu for questions. Application deadline: December 1st in Atlas.

We invite you to study abroad this summer with the College of Computing! Take 12 GT credit hours while immersing yourself in the exciting environments of Barcelona.

Email barcelona@cc.gatech.edu for questions. Application deadline: December 1st in Atlas.

Title: Generative Artificial Intelligence for Uncertainty Quantification

Abstract: Generative artificial intelligence models—including variational autoencoders, normalizing flows, generative adversarial networks, and diffusion models—have dramatically advanced the realism and quality of generated images, text, and audio. Beyond these tasks, generative models hold great promise as powerful tools for probability density estimation and high-dimensional sampling, which are central to uncertainty quantification (UQ) tasks such as amortized Bayesian inference and data assimilation. However, while research on image synthesis emphasizes producing high-quality individual samples, UQ applications require accurate approximation of statistical quantities of interest rather than visually realistic samples. As a result, direct application of existing generative models to UQ problems can lead to biased approximations or unstable training. In this talk, we will introduce several new generative approaches tailored to UQ. These include training-free diffusion models for density estimation, a score-based nonlinear filter for data assimilation, and training-free conditional diffusion models for amortized Bayesian inference. We will demonstrate their effectiveness across a range of tasks, including density estimation for unimodal and multimodal distributions, learning stochastic dynamical systems, parameter estimation via amortized inference, and scalable data assimilation for atmospheric models.

Bio: Dr. Guannan Zhang is a Distinguished Staff Scientist in Computer Science and Mathematics Division at Oak Ridge National Laboratory (ORNL). He earned my Ph.D. in applied mathematics at Florida State University in 2012. He joined ORNL in 2012 as the Householder fellow. He received the DOE Early Career Award in 2022. Guannan's research interests include high-dimensional approximation, uncertainty quantification, machine learning and artificial intelligence, stochastic methods for scientific inverse problems. 

Program Courses:

• CS 4001 – Computing & Society (Ethics Credit) - Students will critically examine how issues around technology, such as globalization, bias, privacy, and others, affect people worldwide.

• CS 3751 – Intro to User Interface Design - Students will explore culturally situated approaches to design and, through the course project, create an inventive design artifact.

Apply HERE. Email indiaprogram@cc.gatech.edu for questions.

Program Courses:

• CS 4001 – Computing & Society (Ethics Credit) - Students will critically examine how issues around technology, such as globalization, bias, privacy, and others, affect people worldwide.

• CS 3751 – Intro to User Interface Design - Students will explore culturally situated approaches to design and, through the course project, create an inventive design artifact.

Apply HERE. Email indiaprogram@cc.gatech.edu for questions and to find out more about upcoming Info Sessions.

Bio: Ferdous Alam is an Assistant Professor in the George W. Woodruff School of Mechanical Engineering at the Georgia Institute of Technology and an affiliated faculty member of ML@GT. He is also a core faculty member at the Institute for Robotics and Intelligent Machines (IRIM). He leads the Inference Lab, where his research focuses on the computational foundations of AI-driven engineering design and robotic manufacturing, including generative modeling of mechanical systems, representation learning for 3D geometry, and robot learning for manufacturing tasks. Before joining Georgia Tech, Dr. Alam was a postdoctoral researcher at MIT, and he previously received his PhD from The Ohio State University. His research has been recognized with several Best Paper Awards at leading ASME conferences, as well as the Google Research Scholar Award in Applied Science.

Zoom Link: https://gatech.zoom.us/j/99778983822?pwd=O0YsaiaJp6ipUrlfIYSHa9ChwbLwXJ.1
Meeting ID: 997 7898 3822 
Passcode: 524773

For CODA guest access, please contact shatcher8@gatech.edu at least 2 business days prior to the event.

Program Courses:

• CS 4001 – Computing & Society (Ethics Credit) - Students will critically examine how issues around technology, such as globalization, bias, privacy, and others, affect people worldwide.

• CS 3751 – Intro to User Interface Design - Students will explore culturally situated approaches to design and, through the course project, create an inventive design artifact.

Applications are now open HERE. Email indiaprogram@cc.gatech.edu for questions and to find out more about upcoming Info Sessions.

Bio: Enric Boix-Adsera is an assistant professor of statistics and data science. His parents are originally from Barcelona, and he grew up mostly in Princeton, New Jersey. Before coming to Wharton, he earned a doctorate in electrical engineering and computer science from MIT.

Boix-Adsera studies the learning processes of artificial intelligence models, such as ChatGPT, with the goal of improving their efficiency and reliability.

 For CODA guest access, please contact shatcher8@gatech.edu at least 2 business days prior to the event.

Bio:  Hal Daumé III is a professor of computer science with appointments in the Maryland Language Science Center and the University of Maryland Institute for Advanced Computer Studies, where he is also the director of TRAILS. In addition to fairness and natural language processing, his research focuses on understanding computational properties of learning and language as well as trustworthy AI.

For CODA guest access, please contact shatcher8@gatech.edu at least 2 business days prior to the event.

The 2026 Fall GT Computing Career Fair takes place Sept. 17 at the McCamish Pavilion. Doors open at 9 a.m. 

The CTRL+CM Speaker Series supports the academic and professional development of computational media students. The series provides educational programming, industry engagement, networking opportunities, and career exploration experiences that enhance student success and workforce preparedness.

Abstract: Neural interface technologies provide new opportunities to assist and augment human behaviors. For instance, muscle activity can be transformed into commands for an assistive device for people with disabilities or provide richer control for a computer than interfaces like mice and keyboards. Connecting signals from the nervous system to an external device in this way presents users with a new, potentially unintuitive, mapping between their movements and those of the device. Users often change their behavior as they learn to control neural interfaces, and many neural interfaces leverage machine learning to let the device adapt to the users. This co-learning creates complex and high-throughput interactions between algorithms and the nervous system. In my talk, I’ll present recent research in my lab demonstrating that the algorithms we use in neural interfaces influence neural computations and user learning. I will then present new computational frameworks we’ve developed to predict and shape user-algorithm interactions. These discoveries open possibilities to build neural interfaces that intelligently interact with the nervous system to assist and rehabilitate motor function across diverse users and applications.

Bio: Dr. Orsborn is a Cherng Jia and Elizabeth Yun Hwang Associate Professor in the departments of Electrical & Computer Engineering and Bioengineering at the University of Washington. Her research explores sensorimotor plasticity in brain-computer interfaces and how plasticity is influenced by the algorithms used. She completed her Ph.D. at the UC Berkeley/UCSF Joint Graduate Program in Bioengineering and her postdoctoral training at NYU’s Center for Neural Science. She recently received the NSF CAREER award, a Sloan Fellowship, and was named an Emerging Leader by the American Institute of Medical and Biological Engineering.

Bio: Jeremy D. Brown, the John C. Malone Assistant Professor in the Department of Mechanical Engineering, explores the interface between humans and robotics, with a specific focus on medical applications and haptic feedback.

Brown’s research sits at the intersection of engineering, biomechatronics, medicine, and psychophysics. He develops novel haptic interfaces for upper-limb prosthetics and minimally invasive surgical robotics. Applications of this research include giving amputees a sense of touch through their prostheses ,and helping surgeons use surgical robots to improve their accuracy and precision when performing delicate procedures.

Join the College of Computing for its annual fall 5K Community Walk/Run. The event focuses on fun and promotes health, wellness, and community. Whether you walk or run, you will connect with students, faculty, staff, alumni, and friends while celebrating school spirit and supporting an active lifestyle.

Bio: Tapomayukh "Tapo" Bhattacharjee is an Assistant Professor in the Department of Computer Science at Cornell University where he directs the EmPRISE Lab (https://emprise.cs.cornell.edu/). He completed his Ph.D. in Robotics from Georgia Institute of Technology and was an NIH Ruth L. Kirschstein NRSA postdoctoral research associate in Computer Science & Engineering at the University of Washington. His primary research interests are in the area of physical robot caregiving and physical human-robot interaction. He is the recipient of TRI Young Faculty Researcher Award'24, NSF CAREER Award'23, AFCEA 40 under 40 Award'22, and his work has won Best Systems Paper Award at HRI’26, Best Paper Award at RSS’25, Best Paper and Student Paper Award Finalist and Best HRI Paper Award Finalist at ICRA’25, Best Systems Paper Award Finalist at HRI'24, Best Demo Award at HRI'24, Best RoboCup Paper Award at IROS’22, Best Paper Award Finalist and ABB Best Student Paper Award Finalist at IROS’22, Best Technical Advances Paper Award at HRI'19, and Best Demonstration Award at NeurIPS’18. His work has also been featured in many media outlets including the BBC, Reuters, New York Times, IEEE Spectrum, and GeekWire and his robot-assisted feeding work was selected to be one of the best interactive designs of 2019 by Fast Company. 

Join the College of Computing Tailgate to celebrate Georgia Tech spirit while connecting with students, faculty, staff, alumni, and friends of the College. This event brings the GT Computing community together for networking, camaraderie, and a fun kickoff to game day traditions.

Bio: Nadia Figueroa is the Shalini and Rajeev Misra Presidential Assistant Professor of Mechanical Engineering and Applied Mechanics at the University of Pennsylvania, with secondary appointments in Computer and Information Science and Electrical and Systems Engineering. She is also a core faculty member of the GRASP Lab. Before joining Penn, she was a Postdoctoral Associate in the Interactive Robotics Group at the Massachusetts Institute of Technology (MIT). She earned her Ph.D. in Robotics, Control, and Intelligent Systems from the Swiss Federal Institute of Technology in Lausanne (EPFL) and previously conducted research at the Robotics and Mechatronics Institute of the German Aerospace Center (DLR) and at NYU Abu Dhabi. She holds a B.Sc. in Mechatronics Engineering from Tecnológico de Monterrey and an M.Sc. in Automation and Robotics from TU Dortmund. Her research focuses on developing integrated learning, control, and estimation algorithms that enable fluid human-robot training, co-existence and collaboration with formal guarantees of safety, efficiency, and robustness. Her work bridges control theory, machine learning, AI, perception, and biomechanics through the lens of physical human-robot interaction. She is a recipient of a 2025 NSF CAREER Award, a finalist for the 2020 Georges Giralt Best Ph.D. and 2017 KUKA Innovation Awards, and has received multiple best paper honors at leading robotics venues such as ICRA, RSS and T-RO.

Bio: Dr. Arash Adel is the founder and director of ARG. He is an assistant professor at the School of Architecture and an associated faculty of the Department of Computer Science at Princeton University. Prior to joining Princeton University in 2023, Adel was an assistant professor of Architecture at the University of Michigan. Adel received his Doctorate in Architecture from the Swiss Federal Institute of Technology (ETH) and his Master’s in Architecture from Harvard University. 

Adel’s research interests include construction robotics, human-robot collaboration, automated building assembly, additive manufacturing, computational design, and STEM education. He is particularly known for his work with novel integrative computational design methods coupled with robotic assembly techniques for manufacturing nonstandard timber buildings and structures. His experience includes numerous widely-published projects such as the DFAB HOUSE located in Dubendorf, Switzerland, and, more recently, the Robotically Fabricated Structure (RFS) timber pavilion sited at the Matthaei Botanical Gardens in Ann Arbor, Michigan, USA.

Bio: TBA

Bio: Sarah Li is an assistant professor at the Daniel Guggenheim School of Aerospace Engineering, a faculty member of the Institute for Robotics and Intelligent Machines, a faculty member of ML@GT, and an affiliate of the Supply Chain and Logistics Institute at Georgia Tech. Her research advances multi-agent models and algorithms to overcome challenges facing future air and space mobility systems. Her technical work lies at the intersection of game theory, stochastic control, and optimization to enable optimal and safe decision-making of autonomous systems in interactive settings. Sarah earned her Ph.D. in Aeronautics and Astronautics from the University of Washington and her B.A.Sc. in Engineering Physics from the University of British Columbia.

Bio: Andrea Bajcsy is an Assistant Professor in the Robotics Institute at Carnegie Mellon University where she leads the Interactive and Trustworthy Robotics Lab (Intent Lab). She broadly works at the intersection of robotics, machine learning, control theory, and human-AI interaction. Prior to joining CMU, Andrea received her Ph.D. in Electrical Engineering & Computer Science from University of California, Berkeley in 2022. She is the recipient of the DARPA Young Faculty Award (2025), NSF CAREER Award (2025), Amazon Research Award (2025), Google Research Scholar Award (2024), Finalist for Best Paper Award of the IEEE RAS Technical Committee on Robot Control (2024), Rising Stars in EECS Award (2021), Honorable Mention for the T-RO Best Paper Award (2020), NSF Graduate Research Fellowship (2016), and worked at NVIDIA Research for Autonomous Driving.

Bio: The Ghosh group engages in cross-disciplinary collaborations and welcomes students from diverse academic backgrounds. Most projects focus on addressing challenges in fundamental physics and astrophysics using computational and AI/ML tools, making the group a natural fit for students with strong skills or interests in these areas. We develop methods to automate theoretical physics calculations using reinforcement learning and LLM agents, enabling rapid testing of new theories. We also work on simulation, experimental design and high-dimensional statistical inference techniques powered by AI to accelerate scientific discovery. Data analysis problems at the scale of the Large Hadron Collider or multi-messenger astronomy often demand rapid decision-making, and we design efficient AI algorithms that can be deployed on fast hardware to meet these challenges.

For CODA guest access, please contact shatcher8@gatech.edu at least 2 business days prior to the event.

Bio: TBA

For CODA guest access, please contact shatcher8@gatech.edu at least 2 business days prior to the event.

Bio: Dr. Navid Azizan is the Alfred H. (1929) and Jean M. Hayes Associate Professor at MIT, where he holds dual appointments in the Department of Mechanical Engineering (in Control, Instrumentation & Robotics) and the Schwarzman College of Computing's Institute for Data, Systems & Society (IDSS) and is a Principal Investigator in the Laboratory for Information & Decision Systems (LIDS). He is also a core faculty member of the Statistics and Data Science Center and the Center for Computational Science and Engineering. His research interests broadly lie in machine learning, systems and control, and mathematical optimization. His research lab focuses on various aspects of reliable AI systems, with applications to high-stakes and safety-critical settings. He obtained his PhD in Computing and Mathematical Sciences (CMS) from the California Institute of Technology (Caltech) in 2020, his MSc in electrical engineering from the University of Southern California in 2015, and his BSc in electrical engineering and physics from Sharif University of Technology in 2013. Prior to joining MIT, he completed a postdoc at Stanford University in 2021. Additionally, he was a research scientist intern at Google DeepMind in 2019. He is a recipient of several awards, including the National Science Foundation CAREER Award, research awards from Amazon, Google, and MathWorks, among others, and the inaugural Information Theory and Applications (ITA) “Sun” (Gold) Graduation Award. His work has been recognized with Best Paper awards at several venues, including the Learning for Dynamics and Control (L4DC), INFORMS JFIG, and ACM Greenmetrics. He was named in the list of Outstanding Academic Leaders in Data by the CDO Magazine for two consecutive years in 2024 and 2023. His teaching and mentorship have been recognized with the Joseph A. Martore (1975) Excellence in Teaching Award in 2026, the Frank E. Perkins Award for Excellence in Graduate Advising (MIT Institute Award) in 2025, and the UROP Outstanding Mentor Award in 2023.

For CODA guest access, please contact shatcher8@gatech.edu at least 2 business days prior to the event.

Bio: I am an applied mathematician interested in the interplay of scientific computing and artificial intelligence. I am a Winship Distinguished Research Associate Professor in the Department of Mathematics and the Department of Computer Science at Emory University and a member of Emory’s Scientific Computing Group. I lead the Emory REU/RET site for Computational Mathematics for Data Science. Prior to joining Emory, I was a postdoc at the University of British Columbia and I held PhD positions at the University of Lübeck and the University of Münster.

For CODA guest access, please contact shatcher8@gatech.edu at least 2 business days prior to the event.

Abstract: This talk investigates the fundamental differences between low-norm and flat solutions of shallow ReLU networks training problems, particularly in high-dimensional settings. We show that global minima with small weight norms exhibit strong generalization guarantees that are dimension-independent. In contrast, local minima that are “flat” can generalize poorly as the input dimension increases. We attribute this gap to a phenomenon we call neural shattering, where neurons specialize to extremely sparse input regions, resulting in activations that are nearly disjoint across data points. This forces the network to rely on large weight magnitudes, leading to poor generalization. Our theoretical analysis establishes an exponential separation between flat and low-norm minima. In particular, while flatness does imply some degree of generalization, we show that the corresponding convergence rates necessarily deteriorate exponentially with input dimension. These findings suggest that flatness alone does not fully explain the generalization performance of neural networks.

Bio: Rahul Parhi is an Assistant Professor in the Department of Electrical and Computer Engineering at the University of California, San Diego. Prior to joining UCSD, he was a Postdoctoral Researcher at the École Polytechnique Fédérale de Lausanne (EPFL), where he worked from 2022 to 2024. He completed his PhD in Electrical Engineering at the University of Wisconsin-Madison in 2022. His research interests lie at the interface between functional and harmonic analysis and data science.

Zoom link: https://gatech.zoom.us/j/93991261775?pwd=PCAJs5vTANpLGiCcKyyBR50hMuV432.1
Meeting ID: 939 9126 1775 
Passcode: 914902

Zoom Meeting Link

If link fails or joining by phone:
Meeting ID: 924 6882 4956
Passcode: 239290
Dial: +1 507 473 4847

Title: Developing Computational Judgment in the Age of AI

Abstract: AI is changing not only how computational work is learned and produced, but also how competence in that work can be evaluated. As AI-supported tools and agentic workflows increasingly shape coding, analysis, modeling, simulation, and explanation, computational education faces an important question: What does it mean to demonstrate competence when final outputs no longer fully reveal the reasoning, verification, and decisions behind the work?

In this talk, Dr. Gaeun (Gwenn) Seo introduces computational judgment as a working construct for studying learners’ ability to evaluate, verify, adapt, and communicate computational outputs and decisions in AI-mediated environments. Drawing on her research in learning systems, competency development, and professional formation in STEM and computational contexts, she connects this construct to broader questions about how students develop and demonstrate computational competence as work changes. The talk outlines a human-centered research agenda for making computational competence more visible, assessable, and responsive to emerging forms of AI-mediated computational learning and work.

Bio: Gaeun (Gwenn) Seo studies how students and professionals develop competence, judgment, and professional direction as AI and computational tools reshape learning and work. Her current research focuses on AI-mediated computational learning and work, computational judgment, STEM doctoral education, and competency development and assessment. She is currently an Academic Professional and Director of Graduate Career Development at Georgia Tech, with promotion to Senior Academic Professional effective August 2026, and serves as Co-PI and research lead on a five-year NSF Innovation in Graduate Education grant studying flexible funding models, industry engagement, internships, and STEM Ph.D. training. Dr. Seo has taught, designed, and evaluated graduate and professional learning experiences across Georgia Tech, Princeton University, Cornell University and Weill Cornell Medicine, and the University of Illinois at Urbana–Champaign. Her teaching has been recognized through “Teacher Ranked as Excellent by Students” honors at both UIUC and Weill Cornell Medicine, and her scholarship has appeared in peer-reviewed journals including the Journal of Career Development, International Journal of Doctoral Studies, and Journal of Further and Higher Education. Her teaching, leadership, and service have received major recognition, including the Georgia Tech Graduate Student Government Association’s Faculty of the Year Award and the Career Services Excellence Award from the National Association of Colleges and Employers (NACE). She earned her Ph.D. from the University of Illinois at Urbana–Champaign, where her dissertation research received the College of Education’s Hardie Dissertation Award.

For scheduling information, please contact Sophie McGivern at smcgivern3@gatech.edu.
For Zoom meeting and recording information, please contact Bryant Wine at bwine3@gatech.edu.

Speaker: Brendan Juba, Associate Professor, Washington University

Abstract:

Domain-independent planning is a classical AI task. For a specified set of objects and predicates, with some initial valuation, an action model is given that describes a set of actions in terms of their preconditions and effects; that is, respectively, properties that the domain must satisfy for an action to execute (e.g., a conjunction), and the changes to the values of predicates that result from the execution. A goal property is also given in terms of the predicates and objects. The domain-independent planning task is then, given this initial valuation, action model, and goal, to output a straight-line program consisting of actions that results in the satisfaction of the goal.

Here, we focus on the task of learning an action model from example executions. We propose a formulation of this task in the spirit of distribution-free PAC learning, that permits an arbitrary domain-independent planner to safely use the action model we produce. Safety here means that we guarantee that any plan produced by the planner executes in the actual action model, i.e., the actual preconditions are satisfied at each step, and results in the satisfaction of the given goal in the actual action model. We show that there are polynomial-time algorithms for safe learning of action models expressible in the classical STRIPS formalism, for example. We will also show that many richer families of domains are not safely learnable.

 Based on joint works with Hai Son Le, Argaman Mordoch, and Roni Stern.

Bio:

Brendan Juba is an Associate Professor in the Department of Computer Science and Engineering at Washington University in St. Louis. His current research interests lie in theoretical approaches to artificial intelligence, founded on the theory of Algorithms and Computational Complexity.

Website: https://www.cse.wustl.edu/~bjuba/

Event Agenda 

• 12:00 – 12:45 PM | Arrival, Lunch, and Networking
• 12:45 – 1:15 PM | Welcome and IRIM Updates - Executive Director Greg Sawicki (Q&A to follow)
• 1:15 – 1:30 PM Break
• 1:30 – 2:45 PM | Research Neighborhood & Research Initiative Updates + All Hands Q&A
• 1:30 – 1:45 PM – Human-Robot Collaborative Teaming | Speaker: Ye Zhao
• 1:45 – 2:00 PM – Agricultural Robotics | Speaker: Colin Usher
• 2:00 – 2:15 PM – Household Robotics | Speaker: Sonia Chernova
• 2:15 – 2:30 PM – Construction Robotics | Speaker: Edvard Bruun
• 2:45 – 4:00 PM  | Poster Session (Atrium) 

REGISTRATION LINK

Speaker:  Ilias Diakonikolas, Professor, The University of Wisconsin–Madison

Abstract:

Robustness is a basic requirement for trustworthy machine learning, yet achieving it efficiently in high dimensions has long been a fundamental challenge. For decades, the prevailing view was that learning algorithms with strong robustness guarantees necessarily come with prohibitive computational cost, creating a sharp tension between statistical guarantees and algorithmic tractability. This talk describes a research program aimed at overcoming this barrier through an algorithmic theory of robust learning. 

 I will describe two interconnected threads within this research program. The first develops a unified framework for efficient robust high-dimensional estimation, including the first polynomial-time algorithms for several fundamental unsupervised learning tasks under adversarial corruption. The second studies supervised learning under noisy labels, with an emphasis on learning predictors with low-dimensional latent representations. I will conclude by discussing future directions, including robustness beyond worst-case corruption and the efficient learning of richer nonlinear representations.

Bio:

lias Diakonikolas is the Lubar Professor in the Department of Computer Sciences at UW Madison. He obtained a Diploma in electrical and computer engineering from the National Technical University of Athens and a Ph.D. in computer science from Columbia University where he was advised by Mihalis Yannakakis. Before moving to UW, he was an Andrew and Erna Viterbi Early Career Chair at USC and a faculty member at the University of Edinburgh. Prior to that, he was the Simons postdoctoral fellow in theoretical computer science at the University of California, Berkeley. His research is on the algorithmic foundations of massive data sets, in particular on designing efficient algorithms for fundamental problems in machine learning. He is a recipient of the ACM Grace Murray Hopper award, a Sloan Fellowship, an NSF CAREER Award, a Romnes Faculty Fellowship, a Google Faculty Research Award, a Marie Curie Fellowship, best paper awards at NeurIPS and COLT, the IBM Research Pat Goldberg Best Paper Award, and an honorable mention in the George Nicholson competition from the INFORMS society. Ilias wrote with Daniel Kane the textbook "Algorithmic High-dimensional Robust Statistics" published by Cambridge University Press.

Date: Wednesday, April 29, 2026, at 12:00 p.m.

Location: Coda, Room 114 (Google Maps link)

Lunch provided!

Title: Safety Alignment of Generative Foundation Models

Abstract: Modern LLMs are safety-aligned through supervised finetuning (SFT) and reinforcement learning from human feedback (RLHF) to mitigate harmful, undesirable, or disallowed outputs. Despite ongoing progress, LLMs still exhibit critical safety gaps: models can be jailbroken into revealing harmful content, often overrefuse benign queries, and fail to maintain safety under adversarial scenarios. My dissertation research advances the safety alignment of generative foundation models by developing principled tools, architectures, and training methods that strengthen their robustness and reliability at scale. Specifically, this thesis focuses on three complementary thrusts: a) Understanding and shaping the safety landscape of LLMs, b) Internalizing safety in agentic reasoning intelligence, and c) Grounding safety and robustness in multimodal perception.

Bio: Anthony is a CS Ph.D. candidate at Georgia Tech working with Polo Chau. His thesis research has elevated foundational AI efforts at Nvidia, Meta, IBM, Intel, and ADP via internships and collaborations, and has resulted in several first-author publications and awards at NeurIPS, ACL, ICCV, EMNLP, CVPR, and BMVC. His research has contributed to the AI foundation of multiple funded industry research grants totaling over $1.4M. Learn more about him at shengyun-peng.github.io.

About HotCSE

HotCSE is an academic seminar series to bring Ph.D. students in Computational Science and Engineering together to discuss interesting topics. The topics consist of high-performance computing, machine learning, data analysis, simulation, computational sustainability, medical informatics, etc.

The talks have always been enjoyable and have ranged from quite informal to formal conference style talks. Either chalks or slides can be used to help people understand your talk. It is also a great forum to practice conference talks and bounce around new ideas.

Currently the talks are sponsored by the School of Computational Science and Engineering. The goal of CSE is slightly broader than that of these talks - we want to bring more people outside CSE to discuss their related work here.

IDEaS-affiliated students and staff are also welcome.

If you do not have access to Coda, near the beginning of the event we will have a staff member or student waiting by the reception desk near the elevators to escort people up.

For questions please contact Ashley.edwards@gatech.edu

Title: Recent Advances in the Design and Simulation of Approximate Multi-Species Collisional Models in Computational Kinetic Theory

Abstract: Kinetic descriptions of particle systems are characterized by a balance of phase-space advection and particles collisions. Often the operators that model collisions are the most expensive part of a kinetic simulation, and simplified models are desired. In this talk, I will present some of these models and discuss recent extensions to the multispecies setting.

Bio: Cory Hauck is an applied mathematician and group leader of the Multiscale Methods and Dynamics Group. His research interests cover various aspects of numerical analysis, computational physics, scientific computing, and mathematical tools for scientific data. His primary research area lies is the development of numerical methods for kinetic equations and related models. These models are characteristic by multiscale phenomena, and their simulation requires advanced mathematical tools in modeling and computation.

Dr. Hauck received his Ph.D. in Applied Mathematics from the University of Maryland in 2006.  Before moving to Oak Ridge, he did a postdoc in the Computational Physics and Methods Group and at the Center for Nonlinear Studies at Los Alamos. He serves on the editorial boards of SIAM Multiscale Modeling & Simulation, Journal of Scientific Computing, and others. He has received Householder Fellowship from ORNL and Early Career Award from the Department of Energy (ASCR).

Location: Klaus Atrium

Who: All students are welcome to participate. 

Register on the site or use the link provided.

Title: Breaking the Scaling Wall in Distributed Deep Learning

Abstract: Significant advances in computer architecture (development of extremely powerful server-class GPUs) and parallel computing (scalable libraries for dense and sparse linear algebra) have contributed to the on-going AI revolution. In particular, distributed training of deep neural networks (DNNs) relies on scalable matrix multiplication algorithms and efficient communication on high-speed interconnects. Pre-training and fine-tuning large language models (LLMs) with hundreds of billions to trillions of parameters and graph neural networks (GNNs) on extremely large graphs requires hundreds to tens of thousands of GPUs. However, such training often suffers from significant scaling bottlenecks such as high communication overheads and load imbalance.

In this talk, I will present several systems research directions that directly impact AI model training. First, I will describe my group's work in using a three-dimensional parallel algorithm for matrix multiplication in large-scale LLM training.  Second, I will demonstrate the application of the same algorithm to full-graph and mini-batch GNN training when working with extremely large graphs. Finally, I will also discuss the need for scalable collective communication routines for large-scale DNN training.

Bio: Abhinav Bhatele is an associate professor in the department of computer science, and director of the Parallel Software and Systems Group at the University of Maryland, College Park. His research interests are broadly in systems and AI, with a focus on parallel computing and distributed AI. He has published research in parallel programming models and runtimes, network design and simulation, applications of machine learning to parallel systems, parallel deep learning, and on analyzing/visualizing, modeling and optimizing the performance of parallel software and systems. Abhinav has received best paper awards at Euro-Par 2009, IPDPS 2013, IPDPS 2016, and PDP 2024, and a best poster award at SC 2023. He was selected as a recipient of the IEEE TCSC Award for Excellence in Scalable Computing (Early Career) in 2014, the LLNL Early and Mid-Career Recognition award in 2018, the NSF CAREER award in 2021, the IEEE TCSC Award for Excellence in Scalable Computing (Middle Career) in 2023, and the UIUC CS Early Career Academic Achievement Alumni Award in 2024.

Abhinav received a B.Tech. degree in Computer Science and Engineering from I.I.T. Kanpur, India in May 2005, and M.S. and Ph.D. degrees in Computer Science from the University of Illinois at Urbana-Champaign in 2007 and 2010 respectively. He was a post-doc and later computer scientist in the Center for Applied Scientific Computing at Lawrence Livermore National Laboratory from 2011-2019. Abhinav was an associate editor of the IEEE Transactions on Parallel and Distributed Systems (TPDS) from 2022-2024. He was one of the General Chairs of IEEE Cluster 2022, and Research Papers Chair of ISC 2023.

Abstract: The ability to manufacture microscale sensors and other components for robotic systems has intrigued the robotics community for almost 40 years. There have been huge success stories; MEMS inertial sensors have enabled an entire market of low-cost, small-scale UAVs. However, the promise of ant-scale robots has largely failed. Ants and other small insects like mites can move at high speeds on surfaces from picnic tables to front lawns, but few small-scale robots have moved outside the lab. This talk will present themes across our work in scaling down robotics. A common thread across our work is the use of geometry, materials, and mechanisms to do part of the robot control and computation in hardware. For example, choosing the right foot geometry and size scale can result in a 3.6 cm high power autonomous biped capable of high speed locomotion at 25 cm/s. Novel fabrication processes can be designed to tightly couple high-bandwidth actuators, sensors, and mechanisms for locomotion and manipulation tasks. Finally, even sensors can be designed to quickly and easily detect flight-relevant events. 

Bio: Sarah Bergbreiter joined the Department of Mechanical Engineering at Carnegie Mellon University as a Professor in the fall of 2018 after spending ten years at the University of Maryland, College Park. She started her academic career with a B.S.E. degree in electrical engineering from Princeton University in 1999. After a short introduction to the challenges of sensor networks at a small startup company, she received her M.S. and Ph.D. degrees from the University of California, Berkeley in 2004 and 2007 with a focus on small-scale robots. Prof. Bergbreiter received the DARPA Young Faculty Award in 2008, the NSF CAREER Award in 2011, and the Presidential Early Career Award for Scientists and Engineers (PECASE) in 2013 for her research on engineering robotic systems down to millimeter size scales. She has received several Best Paper awards at conferences like ICRA, IROS, and Hilton Head Workshop with her fabulous group of students and former students, and is a Fellow of the ASME. She also served as Vice Chair of DARPA’s Microsystems Exploratory Council from 2020 through 2022. Outside of academia, she enjoys spending time with her husband and two daughters, running, biking, or skiing outside rather slowly, and the rare game of water polo.

Date: Wednesday, April 1, 2026, at 12:00 p.m.

Location: Coda, Room 230 (Google Maps link)

Lunch provided!

Title: Fast Active-Set Thresholding Method for Nonnegative Least Squares

Abstract: Nonnegative Least Squares (NNLS) is a fundamental constrained optimization problem encountered in many applications such as image deblurring, signal processing, nonnegative matrix factorization, magnetic microscopy, and hyperspectral imaging. Active-set based methods are a common class of algorithms for solving NNLS which identify the optimal variable set of the NNLS solution. They do so by iteratively solving a series of unconstrained least squares problems, identifying which variables violate the nonnegativity constraints, and then swapping variables in/out of consideration until the optimal set of variables is found. Several variations improving upon this method exist in the literature. In this work, we propose an active-set swap heuristic which further improves upon existing active-set based methods for NNLS. Our optimizations are based upon adding multiple variables to the passive set within a threshold of the smallest gradient value and removing variables within a similar threshold of the closest boundary constraint. We leverage these optimizations to yield a Fast Active-Set Thresholding NNLS (FAST-NNLS) algorithm which significantly outperforms the existing state-of-the-art NNLS algorithms for a wide range of problems. Rigorous convergence guarantees are proven for the proposed method. We demonstrate the effectiveness of our proposed method on multiple synthetic datasets and two real-world text analysis applications. In doing so, we present the most comprehensive NNLS solver comparison in the literature to date.

Bio: Ben Cobb is a CSE Ph.D. candidate conducting research at the intersection of high-performance computing and numerical linear algebra under the co-advisement of Richard Vuduc and Haesun Park. His doctoral research pertains to various forms of tensor decompositions for data analysis and compression.

About HotCSE

HotCSE is an academic seminar series to bring Ph.D. students in Computational Science and Engineering together to discuss interesting topics. The topics consist of high-performance computing, machine learning, data analysis, simulation, computational sustainability, medical informatics, etc.

The talks have always been enjoyable and have ranged from quite informal to formal conference style talks. Either chalks or slides can be used to help people understand your talk. It is also a great forum to practice conference talks and bounce around new ideas.

Currently the talks are sponsored by the School of Computational Science and Engineering. The goal of CSE is slightly broader than that of these talks - we want to bring more people outside CSE to discuss their related work here.

Speaker: Steven Xia, Ph.D. Candidate, University of Illinois Urbana-Champaign

Abstract:

AI and large language models (LLMs) are ushering in a new era of software development, fundamentally reshaping how systems are built, tested, and maintained. In this talk, I will present my research on integrating modern LLM capabilities with core software engineering principles to automate complex development tasks and strengthen the coding and reasoning abilities of AI systems. I will first introduce TitanFuzz, which leverages LLMs to implicitly solve complex and heterogeneous constraints for large-scale system testing, uncovering critical bugs in real-world software, and inspiring extensive subsequent work in LLM-driven testing. Next, I will discuss Agentless, which demonstrates that a simple, lightweight framework can effectively solve challenging repository-level software engineering tasks without heavy agentic overhead. I will showcase how Agentless has been adopted by leading AI companies to evaluate their latest models, inspire new agentic frameworks, and perform post- or mid-training for agentic coding and reasoning. In addition, I will highlight my other work on automating complex software tasks and my recent work to enable runtime self-improvement in AI coding systems. Together, my work establishes a scalable and practical foundation for building more capable and reliable AI-driven software systems.

Bio:

Chunqiu Steven Xia is a PhD candidate in Computer Science at UIUC, advised by Professor Lingming Zhang. His research lies at the intersection of Software Engineering and Artificial Intelligence, with a focus on automating critical and cognitively demanding software development tasks using large language models (LLMs) and software agents. His work has significantly advanced how fundamental software problems are addressed in both academia and industry, uncovering 200+ critical bugs and vulnerabilities in widely used systems, and being adopted by leading AI companies, including OpenAI, Meta, DeepSeek, and MiniMax. His research has been recognized with an ACM SIGSOFT Distinguished Paper Award (FSE 2025), an Oral Spotlight Paper Award (COLM 2024), a CACM Research Highlight (FSE 2023), and the prestigious Amazon AICE PhD Fellowship.

Title: Diffusion Models for the Next Generation of Simulation-Based Inference: Challenges and Opportunities

Abstract: Diffusion models have recently emerged as powerful tools for simulation-based inference (SBI). SBI tackles the problem of estimating complex models from complex data, and the score-based formulation of diffusion models offers unmatched flexibility for inference and generation. This talk will synthesize recent advancements in diffusion models for SBI, focusing on key developments in training, inference, and evaluation. It will explore the potential of concepts such as guidance, score composition, flow matching, consistency models, and joint modeling. Finally, it will showcase three recent contributions from our group: 1) consistency models for near-real-time Bayesian inference; 2) compositional models for large-scale multilevel estimation, and 3) amortized Bayesian adaptive design for maximizing information gain in sequential experiments.

Bio: Stefan T. Radev is the principal investigator of the BayesOps Lab. He leads research on amortized Bayesian inference with generative AI and is a core developer and originator of the BayesFlow framework. He is particularly interested in the intersection of Bayesian modeling, deep learning, and cognitive science. His education and experience include:

2018 – 2021 – Ph.D., Heidelberg University (Statistical Modeling in Psychology)
2021 – 2023 – Postdoctoral Researcher, Heidelberg University (Deep Learning)
2023 – present – Assistant Professor, Rensselaer Polytechnic Institute

This talk will be broken into two parts. First, we will talk about the hardware design of humanoid robots, in particular the design of IHMC's custom humanoids, Nadia and Alex. These systems are highly articulated and thus highly complex, with many degrees of freedom and many subsystems. Beyond complexity, however, enabling them to move through environments dynamically and efficiently requires careful consideration of not only their actuator design but also the passive dynamics. Then, we will talk about IHMC's work in the design of autonomy and human interfaces to enable humans to team with humanoid robots to explore and work in novel environments. This will overview the approach for one of the earliest uses of virtual reality to control humanoid robots.  We will also highlight IHMC's design of a flexible autonomy architecture built on behavior trees that enables on-the-fly drafting of novel behaviors and reliable reactivity, including the inclusion of human intervention when encountered with uncertainty.

Bio: Dr. Robert Griffin is a Senior Research Scientist at IHMC and Director of Research Professor at the University of West Florida. His research focuses on improving mobility and autonomy for legged robotics and powered exoskeletons. He is interested in system level approaches for improving the mobility and capability of these robotic platforms, including platform design, motion design and control, autonomy and manipulation, and perception. 

Dr. Griffin leads the robotics group at IHMC, directing a number of projects focusing on advancing robotics. This has included the Office of Naval Research's SquadBot program, which has led to the development of the Alex and Nadia humanoid robots. He has also led the algorithm development for NASA Johnson Space Center's Valkyrie project, including using Valkyrie as an Explosive Ordnance Disposal Technician. Dr. Griffin has also guided the development of a number of exoskeleton systems, including devices used for regaining mobility as well as worker assistance for the Department of Energy. The research in these projects has included the development of novel simplified models for locomotion, contact planning, environmental modeling, the development of autonomy algorithms, and hardware design. His work has resulted in a number of recognitions, including several best paper awards, qualifying as a finalist in the Toyota Mobility Foundation's Mobility Unlimited Challenge, a 2nd and 4th place finish in the Cybathlon Powered Exoskeleton race, and being named as the Outstanding Research Organization in the 2025 Humanoid Robotics Industry Awards. 

Dr. Griffin earned his bachelor’s degree from Tennessee Tech University, and his Ph.D. from Virginia Tech in 2017 with a primary research focus on the control of bipedal robotic mobility for humanoids and exoskeletons. This includes the Shipboard Autonomous Firefighting Robot with ONR and Virginia Tech’s entry into the 2015 DARPA Robotics Challenge.

Title: Toward Foundation Agents: How Multimodal Models Learn (and Fail to Learn) the Physical World

Abstract: Today’s multimodal models are often trained with a brute-force “align everything” recipe, yet it is still unclear how cross-modal intelligence can emerge. We argue the key question is mechanistic: how can models go beyond static alignment annotations to learn from physical-world interaction and support goal-directed decision making? We systematically study multimodal learning through the MDP agent loop: state estimation, world modeling for planning, and control for safety. First, we open up the black box, and intervene inside embeddings to reveal how geometry is lost, and design ways to retain geometric structure. Second, we inject world-model priors to teach dynamics through RAGEN/VAGEN, enabling multi-step planning rather than token matching. Third, we introduce ODE-Steer for safe agents, which steers internal activations into “safe zones” where reasoning stays reliable and controllable. Lastly, we lay out the future that true multimodal intelligence requires more than aligning tokens; it requires aligning the internal mechanisms of the model with the geometry of the world.

Bio: Manling Li is an Assistant Professor at Northwestern University and an Amazon Scholar. She was a postdoc at Stanford University, and obtained Ph.D. degree in Computer Science at University of Illinois Urbana-Champaign in 2023. She works on Reasoning, Planning and Compositionality, in the intersection of Language, Vision, and Robotics. Her work has been recognized as ACL 2025 Inaugural Dissertation Award Honorable Mention, MIT Tech Review Innovators Under 35, ACL’24 Outstanding Paper Award, NAACL'21 Best Demo Paper Award, ACL'20 Best Demo Paper Award, Microsoft Research PhD Fellowship, EE CS Rising Star, etc. She served as virtual chairs of ACL 25, publication chairs at NAACL 25, demo chairs at EMNLP 24, etc. Additional information is available at https://limanling.github.io/.

Date: Wednesday, March 4, 2026, at 12:00 p.m.

Location: Coda, Room 230 (Google Maps link)

Lunch provided!

Title: From Sparse Sensors to Continuous Fields: STRIDE for Spatiotemporal Reconstruction

Abstract: We introduce STRIDE (Spatio-Temporal Recurrent Implicit DEcoder), a novel deep learning framework for reconstructing high-dimensional spatiotemporal fields from sparse point-sensor measurements. Existing approaches often struggle to generalize across trajectories and parameter settings, or rely on discretization-tied decoders that do not naturally transfer across meshes and resolutions. Our proposed approach is a two-stage framework which maps a short window of sensor measurements to a latent state with a temporal encoder and reconstructs the field at arbitrary query locations with a modulated implicit neural representation (INR) decoder. Using the Fourier Multi-Component and Multi-Layer Neural Network (FMMNN) as the INR backbone improves representation of complex spatial fields and yields more stable optimization than sine-based INRs. We provide a conditional theoretical justification: under stable delay observability of point measurements on a low-dimensional parametric invariant set, the reconstruction operator factors through a finite-dimensional embedding, making STRIDE-type architectures natural approximators. Experiments on four challenging benchmarks spanning chaotic dynamics and wave propagation show that STRIDE outperforms strong baselines under extremely sparse sensing, supports super-resolution, and remains robust to noise.

Bio: Yanjie Tong is a second-year CSE Ph.D. student advised by Dr. Peng Chen. He earned both his B.S. in Mathematics and Physics and his B.Eng. in Energy and Power Engineering at Tsinghua University. His research focuses on methods for learning latent dynamics in low-dimensional spaces and their application to real-world problems.

About HotCSE

HotCSE is an academic seminar series to bring Ph.D. students in Computational Science and Engineering together to discuss interesting topics. The topics consist of high-performance computing, machine learning, data analysis, simulation, computational sustainability, medical informatics, etc.

The talks have always been enjoyable and have ranged from quite informal to formal conference style talks. Either chalks or slides can be used to help people understand your talk. It is also a great forum to practice conference talks and bounce around new ideas.

Currently the talks are sponsored by the School of Computational Science and Engineering. The goal of CSE is slightly broader than that of these talks - we want to bring more people outside CSE to discuss their related work here.

The world around us is inherently 3D, and this structure is essential from engineering and the physical sciences to photogrammetry and robotics. Yet computing and learning with real-world geometric data remains remarkably difficult, stubbornly stuck on challenges of robustness, representation, and scale. Noisy scans, mismatched representations, and massive datasets make even basic operations fragile and slow, while learning with 3D data demands a new set of architectures purpose-built for the task.

This talk will present methods that unlock 3D data for reliable processing and learning in the wild. I'll cover neural network architectures designed specifically for 3D data to offer physical consistency and geometric fidelity by-construction, simulation techniques that operate natively on scanned environments, and the foundational geometric algorithms that underpin it all. Throughout, a key theme is interfacing principled geometric methods with modern machine learning.

Bio

Nicholas Sharp's research develops algorithms and architectures to make computing with geometric data easy, efficient, and reliable. He received his PhD in Computer Science from Carnegie Mellon University advised by Keenan Crane, and completed his postdoc at the University of Toronto & Fields Institute for Mathematics with Alec Jacobson. Currently, he is a Senior Research Scientist at NVIDIA, leading research on 3D learning that powers applications from autonomous driving to generative AI. His work has won multiple best paper awards (SIGGRAPH '22, SIGGRAPH Asia '23, SGP '20 & '25), developed widely-used software including the award-winning Polyscope library, and has been covered in the press by the New York Times and Ars Technica. For more, see www.nmwsharp.com.

Bio

Yifei Li is a Ph.D. candidate in EECS at MIT, advised by Prof. Wojciech Matusik. Her research bridges high-fidelity physics simulation with machine learning to enable systems that reason through physical environments, powering applications across computational design, digital twins, assistive robotics, and biomedical engineering. Yifei received her B.S. in Computer Science from Carnegie Mellon University. Her professional experience includes research internships at Meta Reality Labs, NVIDIA, the Boston Dynamics AI Institute, and Facebook AI Research. She is the recipient of the MIT Stata Family Presidential Fellowship and has been named a Rising Star in both Computer Graphics and EECS.

What AI tools have you tried for writing, finding literature citations, making presentations, coding, or automating research tasks?  Come share your experiences and learn from others over coffee with the IDEaS community.

IDEaS-affiliated students and staff are also welcome.

If you do not have access to Coda, near the beginning of the event we will have a staff member or student waiting by the reception desk near the elevators to escort people up.

For questions please contact Ashley.edwards@gatech.edu

Physics simulation increasingly sits in the loop of interactive content creation, digital twins, and embodied AI. A central dilemma cuts across these applications: the tradeoff between simulation speed and fidelity, especially at scale. In practice, an equally limiting barrier is interactive control. Artists and designers need coarse previews they can manipulate in real time, with confidence that refinement will not overturn their decisions. Standard multiresolution approaches often fall short because coarse solutions can drift, and refinement can introduce surprises due to numerical stiffening, geometric inconsistency, and contact.

To address this challenge, my research program introduces Progressive Simulation, a general-purpose, coarse-to-fine level-of-detail (LOD) framework for physics simulation that brings and generalizes ideas from progressive rendering and progressive geometry to the simulation setting. The core idea is to produce a fast, coarse, artifact-free, predictive preview under tight computational budgets for rapid iteration, then apply consistent refinement across resolutions that converges to a richly detailed, high-fidelity result as more resources or stricter accuracy requirements become available. In this talk, I will present methods that realize this approach in both progressive quasistatics and progressive dynamics, with results spanning cloth, shells, and volumetric objects, enabling experimental design, interactive staging, and physics-based storytelling. Finally, I will outline future directions toward broader applicability, including multi-fidelity, multi-physics simulation systems powered by scalable solvers.

Bio

Jiayi (Eris) Zhang is a fifth-year PhD candidate in Computer Science at Stanford University, advised by Prof. Doug James, and works closely with Dr. Danny Kaufman at Adobe. She received her BS in Computer Science and Mathematics from the University of Toronto, where she conducted research with Prof. Alec Jacobson. Her research spans physics simulation, geometry processing, numerical optimization, and spatial intelligence, with a focus on building algorithms, models, and tools that enhance human productivity and creativity in science, engineering, and interactive authoring workflows. She is a Stanford Reed-Hodgson Fellow, a WiGRAPH Rising Star, and an MIT EECS Rising Star, and has received the Adobe Women-in-Technology Scholarship, the Roblox Graduate Fellowship, and the NVIDIA Graduate Fellowship. She has also interned at Adobe and NVIDIA across multiple summers.

Title: Symbolic Abstractions Enable Exascale Simulations of Reacting Flows and Automatic Differentiation

Abstract: Accurate simulations of reacting flows require a computational representation of the chemical source terms. Dedicated libraries can provide such representations, acting as interfaces between mechanistic data and flow solvers. However, libraries form a fragmented computational landscape, designed to satisfy one application (e.g., combustion or plasma chemistry) and target specific computing hardware. These considerations preclude the simulation of multi-chemistry flows such as plasma-coupled combustion, automatic differentiation, and joint optimization of flow solvers on modern hardware such as GPUs. A symbolic representation of the chemistry is developed to address these challenges. At the symbolic level, conflicts across applications and hardware vanish. The representation is language and library agnostic, transformed through code generation to enable performant GPU execution and automatic differentiation. The Pyrometheus suite implements the proposed approach. Its capabilities and performance are demonstrated for combustion, plasma, and thermonuclear chemistry. The implementation supports existing HPC frameworks, enabling exascale simulations of reacting flows with the state-of-the-art flow solver MFC.

Bio: Esteban Cisneros–Garibay is an assistant professor at the University of Tennessee Space Institute. His research focus is on high-speed chemically-reacting turbulent flows, using computational methods. He obtained his PhD in Theoretical & Applied Mechanics at The University of Illinois Urbana–Champaign in 2021. From 2021 to 2022, he was Presidential Postdoctoral Fellow at Princeton University, and then a data scientist at Bayer AG until 2025. 

World models that recreate and simulate the physical world hold transformative potential across robotics, entertainment, and engineering analysis. Achieving this vision requires both generating 3D environments from limited observations and predicting how they evolve under physical actions. Pure physical modeling provides guarantees and action control but demands complete state specification rarely available in practice; pure generative learning handles incomplete information to produce realistic content but lacks the structured representations needed for physical interaction and reasoning. This talk presents physics-grounded world models, integrating these approaches to leverage their complementary strengths: physical representations provide the structured interface for actions and consistency guarantees, while generative models supply visual realism and compensate for incomplete observations. I will demonstrate this framework across two core capabilities---generating 3D worlds from single images and simulating dynamics under physical actions---and show how it extends to real engineering problems in fluid and thermal analysis.

Bio

Hong-Xing (Koven) Yu (https://kovenyu.com/) is a PhD candidate at the Computer Science Department of Stanford University, advised by Prof. Jiajun Wu. His research focuses on physics-grounded world models. He is a recipient of the SIGGRAPH Asia Best Paper Award, the Stanford SoE Fellowship, the Qualcomm Fellowship, and the Meshy Fellowship, and a finalist of the NVIDIA Fellowship, the Meta Fellowship, the Jane Street Fellowship, and the Roblox Fellowship.

Speaker:  Shanto Rahman, Ph.D. Candidate, University of Texas at Austin 

Abstract: 

Software testing is one of the most scalable ways to check program correctness. However, nondeterminism in test execution and rapid code evolution can cause tests to break and produce false failures, where the same test may fail without any underlying bug. As these false failures accumulate, developers may start ignoring test results, allowing real bugs to reach production. My research aims to make software testing reliable by detecting, understanding, reproducing, and repairing such broken tests. In this talk, I first present my work on predicting and diagnosing the root causes of flaky tests using context-aware attribution, helping developers understand why nondeterministic failures occur while reducing runtime and memory cost. Next, I introduce automated repair techniques for both nondeterminism- and evolution-induced test breakage using intent-preserving dynamic instrumentation and generative AI. These techniques are evaluated on large-scale, real-world datasets, and achieve high repair success. I conclude by outlining a path from reliable test diagnosis and repair, extending these reliability foundations to modern computing systems for trustworthy, safe operation in practice. 

Bio: 

Shanto Rahman is a final-year Ph.D. candidate at The University of Texas at Austin, advised by August Shi. Her research sits at the intersection of software engineering, program analysis, and AI, with a focus on making software testing reliable under nondeterminism and continuous code evolution. Her work has been published in top venues including ICSE, OOPSLA, ASE, and ICST. Shanto has gained industry experience through research internships at Google and Amazon Web Services (AWS). She has been recognized as an MIT EECS Rising Star and has received multiple UT Austin fellowships and awards. 

Abstract: Modern machine learning systems achieve impressive performance, but are largely built under a closed-world assumption: that the data distribution does not change from the distribution of the training set.  Real environments are open, dynamic, and filled with unknown unknowns. In such settings, knowing when a model’s output is reliable is critical.

This talk focuses on out-of-distribution (OOD) detection, a key capability for safe and reliable AI. The first part presents a mathematical theory of OOD detection that places state-of-the-art methods, largely heuristically derived, within a unified variational information-theoretic framework [1].  The theory provides plausible assumptions behind existing approaches and predicts new OOD detectors that are simple to implement and outperform state-of-the-art methods.

The second part of the talk addresses an often overlooked problem in practical deployment of OOD detectors, that is, OOD detectors depend on parameters that must be tuned, and a “given OOD” dataset is required [2]. In practice, such given OOD data may be difficult to obtain.  We formalize this problem and introduce a new tuning strategy that uses only the model’s training data and achieves similar or better performance compared to tuning on given OOD data, enabling robust and practical deployment.

The ideas will be illustrated across applications including automatic target recognition, cyber-security, large language models, and radio-frequency (RF) fingerprinting.

[1] https://arxiv.org/pdf/2506.14194

[2] https://arxiv.org/pdf/2602.05935

Bio: Dr. Ganesh Sundaramoorthi is Senior Research Fellow/Director of Research at RTX Technology Research Center, which is the research center for RTX (encompassing Raytheon, Collins Aerospace, and Pratt & Whitney) and also Adjunct Professor of ECE at Georgia Tech.  His research is in machine learning, computer vision, and artificial intelligence (AI), e.g., robustness, explainability, acceleration, and low size, weight & power.  Prior to his current position, he was on the faculty of KAUST, where he led a research group in computer vision.  His PhD was from Georgia Tech and he did postdoctoral work at UCLA in computer vision. He has led a number of internal and external research programs in AI including IARPA, NGA, ARPA-E and AFRL.  He was area chair for leading AI conferences (IEEE/CVF CVPR & ICCV). He has more than 60 publications in AI and nearly 50 patents and/or applications.

http://ganeshsun.com/

For more information, or for CODA guest access, please contact shatcher8@gatech.edu at least 2 business days prior to the event.

ZOOM ACCESS 

https://gatech.zoom.us/j/92002341992?pwd=ZLAiI8WdAu8arEo23SEArIhGU2smxm.1

Meeting ID: 920 0234 1992 
Passcode: 253459 

As we move toward the era of physical AI systems that perceive, reason, and act, the demand for virtual worlds that behave like reality has never been higher. My work targets this challenge through 'Physically Grounded Visual Computing': a perspective that bridges high-fidelity computer graphics engines with modern 3D vision, generative AI, and robots. I will present our breakthroughs in robust graphical simulations, specifically showing how continuum mechanics and contact mechanics provide the mathematical guarantees needed to model complex phenomena, from glacial calving to tactile manipulation. Beyond dynamic simulations, I will discuss how we are fusing these engines with generative models, such as physics-informed 3D Gaussian Splatting, video diffusion, and 3D reconstruction models, to create digital twins that look photorealistic and act physically valid. We build towards a roadmap for using these physics-based world engines to generate synthetic data at scale and equip agents with the physical intuition they need to succeed in the real world.

Bio

Chenfanfu Jiang (PhD’15) is a Professor of Mathematics and the director of the Artificial Intelligence and Visual Computing (AIVC) Lab at UCLA. He primarily works on computer graphics and its interdisciplinary synergies with 3D vision, generative AI and physical AI. He has led the development of widely-adopted simulators with Particle-In-Cell, Material Point, and Incremental Potential Contact methods. He received the dissertation award from UCLA, NSF CAREER, and multiple faculty awards from Amazon, Style3D, and Sony, as well as best paper awards/honorable mentions at SIGGRAPH, SCA, MIG, ICRA, and IROS.

Speaker:  Sourav Chakraborty, Professor, Indian Statistical Institute

Abstract: 

The problem of testing whether an input satisfies a given property can be significantly easier than estimating the input’s distance from having that property. However, for certain classes of properties, these tasks may be quite similar.

One of the newer models for testing distribution properties is the huge object model, introduced by Goldreich and Ron in 2023. In this talk, we investigate the query complexity of testing index-invariant properties within this model. We adapt Szemerédi’s regularity method to this setting and prove that, for index-invariant properties, constant query testability implies constant-query estimability.

This talk is based on the following works:

1. “Testing vs Estimation for Index-Invariant Properties in the Huge Object

Model,” joint work with Eldar Fischer, Arijit Ghosh, Amit Levi, Gopinath Mishra,

and Sayantan Sen, STOC 2025.

2. “Testing of Index-Invariant Properties in the Huge Object Model,” joint work

with Eldar Fischer, Arijit Ghosh, Gopinath Mishra, and Sayantan Sen, COLT 2023

Bio:

Sourav Chakraborty is a Professor in the Advanced Computing and Microelectronics Unit (ACMU) of the Computer and Communication Sciences Division (CCSD) at the Indian Statistical Institute (ISI), Kolkata, India. Before joining ISI in July 2018, he was a faculty member at the Chennai Mathematical Institute, India, from September 2010. He completed his PhD in Computer Science in June 2008 at the University of Chicago under the supervision of Prof. László Babai and did postdoctoral stints at Technion, Israel, and CWI, Amsterdam.

Speaker:  Courtney Miller, Ph.D. Candidate, Carnegie Mellon University 

Abstract: 

Software development is shaped by constant disruption—from open-source dependency abandonment to generative AI (GenAI) tools fundamentally reshaping how code is written. 
 
In this talk, I'll present two lines of work, each examining a different disruption. First, I'll share my work on the disruption of open source dependency abandonment, revealing the unsupported challenges developers face when identifying and responding to abandonment, identifying factors that support successful downstream response, and demonstrating how theory-driven LLM-based systems can make those risks more visible. Second, I’ll present findings from my recent collaboration with Microsoft Research about the disruption of GenAI adoption on development teams, demonstrating why adoption succeeds for some developers but stalls for others in seemingly similar contexts, showing the amplification effect organizational support mechanisms can have, and introducing the Productivity Pressure Paradox: a dynamic where increased productivity expectations without corresponding support can actually prevent developers from building the skills that would deliver those gains. 
 
Finally, I’ll outline my research vision for helping developers anticipate and navigate the disruptions of tomorrow—from building AI-powered tools for software supply chain resilience to studying how GenAI is reshaping development team practices and processes. 

Bio:

Courtney Miller is a Software Engineering Ph.D. Candidate in the School of Computer Science at Carnegie Mellon University, co-advised by Bogdan Vasilescu and Christian Kästner. Her research examines how developers navigate technological disruptions—from dependency abandonment threatening open source software supply chain sustainability and security to generative AI adoption reshaping development workflows. 
 
Her empirical approach combines human-centered qualitative techniques with large-scale data-driven analysis, modeling, and visualization to inform the development of theoretically-grounded insights and practice-driven tooling solutions. As part of the Secure Software Supply Chain Center (S3C2), her work has informed security practices through contributions to federal agency and industry supply chain security summits. 
 
Courtney has earned three ACM SIGSOFT Distinguished Paper Awards at the International Conference on Software Engineering (ICSE) and an NSF Graduate Research Fellowship. She has conducted two research internships at Microsoft Research. She holds a B.A. with honors in Computer Science and Statistics from New College of Florida. In her free time, she enjoys indoor cycling and leisurely walks with her 14-year-old toy poodle Chanel. 

Date: Tuesday, February 17, 2026 at 11:00 am

Location: Coda Building, Room 114 (Google Maps link)

Link: The recording of this in-person seminar will be uploaded to CSE's MediaSpace

Coffee and snacks provided!

Title: Uncompromising Performance with Exocompilation

Abstract: Performance is the currency of modern computing. Achieving peak throughput on fast‑evolving accelerators demands more control than today's compilers provide. I will present Exo and the Exocompilation paradigm: a user‑schedulable programming language that shifts two responsibilities traditionally hard‑coded in compilers--hardware backends and optimization strategies--into safe, extensible user libraries. In Exo, optimizations are expressed as verified rewrites that guarantee functional equivalence, and low‑level primitives (e.g., explicit instruction selection, GPU asynchrony) give programmers precise control. This design enables targeting CPUs, GPUs, and matrix engines, and supports concise, reusable scheduling libraries that match or surpass the performance of state-of-the-art libraries such as cuBLAS and MKL. Exo‑generated kernels already ship at scale, including on Apple devices.

Bio: Yuka Ikarashi is a sixth-year Ph.D. candidate at MIT CSAIL. She received her M.S. from MIT in 2022 and her B.S. from the University of Tokyo in 2020. Passionate about compilers and programming languages for high-performance computing, she created the Exo programming language. She has previously worked at Apple, Amazon, and CERN, applying her research to various accelerators and applications. She has been awarded the Quad Fellowship, the Masason Foundation Fellowship, the Funai Foundation Fellowship, the ML and Systems Rising Stars Award, and the Rising Stars in EECS Award. Originally from Tokyo, Japan, she is an avid traveler and has visited 36 countries.

In this talk, I will describe how we achieve this in a material-like robotic collective by modulating the interunit tangential forces to control topological rearrangements of units within a tightly packed structure. This allows local control of rigidity transitions between solid and fluid-like states in the collective and enables spatiotemporal control of shape and strength. I will show examples of structure-forming and healing and how the collective can support 700 newtons (500 times the weight of a robot) before“melting” under its own weight.

Bio:  Elliot W. Hawkes is an Associate Professor of Mechanical Engineering at UCSB. He completed a postdoctoral fellowship at Stanford University, where he also earned his MS and PhD in Mechanical Engineering. Previously, he worked at the Harvard Microrobotics Lab and the ETH Multi-scale Robotics Lab. The Hawkes Lab's research is at the intersection of design, mechanics, and materials, and develops novel mechanisms and applies non-traditional materials to solve challenging problems in robotics, medicine, and biomechanics. He has spun two companies out of the Hawkes Lab, to bring new medical and rehabilitation devices into the world.

Title: Expediting Next-Generation AI for Health via KG and LLM Co-Learning

Abstract: Large language models (LLM) have brought disruptive progress to information technology from accessing data to performing analytical tasks. While demonstrating unprecedented capabilities, LLMs have been found unreliable in tasks requiring factual knowledge and rigorous reasoning, posing critical challenges in domains such as healthcare. Knowledge graphs (KG) have been widely used for explicitly organizing and indexing biomedical knowledge, but the quality and coverage of KG are hard to scale up given the notoriously complex and noisy healthcare data with multiple modalities from multiple institutions. Existing approaches show promises in combining LLMs and KGs to enhance each other, but they do not study the techniques in real healthcare contexts and scenarios. In this talk, I will introduce our research vision and agenda towards KG-LLM co-learning for healthcare, followed by success examples from our recent exploration on LLM-aided KG construction, KG-guided LLM enhancement, and federated multi-agent systems. I will conclude the talk with discussions on future directions that can benefit from further collaborations with researchers interested in data mining or biomedical informatics in general.

Bio: Carl Yang is an Assistant Professor of Computer Science at Emory University, jointly appointed in the Rollins School of Public Health and Nell Hodgson Woodruff School of Nursing. He received his Ph.D. in Computer Science at University of Illinois, Urbana-Champaign in 2020, and B.Eng. in Computer Science and Engineering at Zhejiang University in 2014. His research areas span data mining, deep learning, multimodality foundation models and trustworthy AI, with applications in graph analytics, neuroscience, biomedicine and healthcare. Carl's research results have led to 250+ peer-reviewed publications in top venues across AI/ML and medicine/healthcare. He serves as the Organizer of Health Day and Inaugural Program Chair of AI4Sciences in KDD, and the Chair-Elect of AMIA KDDM Working Group. He is also a 1% NIH/CDC Grant Awardee in 2025, and a recipient of the ACM SIGKDD Rising Star Award in 2025 (one winner a year in the world), NSF CAREER Award in 2025, NIH K25 (Career) Award in 2023, and multiple Best Paper Awards such as of MedInfo 2025, KDD Health Day 2022, ML4H 2022, and ICDM 2020.

Date: Thursday, February 12, 2026 at 11:00 am

Location: Coda Building, Room 114 (Google Maps link)

Link: The recording of this in-person seminar will be uploaded to CSE's MediaSpace

Coffee and snacks provided!

Title: Discovering Model Manifolds of Emergent Function from High-Dimensional Data

Abstract: Natural systems of many interacting constituents often organize to produce low-dimensional emergent behaviors. For example, hundreds of thousands of neurons in the brain coordinate to represent and navigate the three-dimensional world around us. Similar emergent behaviors arise in the tens of thousands of genes that coordinate to produce the cellular processes that maintain life. Recent technological advances now allow us to simultaneously measure the activity of tens of thousands of neurons in the brain, and the expression of every gene at the resolution of single cells, giving us the opportunity to model emergent function at an unprecedented scale. How do we take such high dimensional data and discover interpretable and quantitative models of the algorithms that brains use to navigate the world, and cells use to achieve life? 

In this talk, I will discuss novel methods I am pioneering that combine differential geometry with deep neural networks to quantitatively model emergent behaviors using high-dimensional, high-throughput data from neuroscience and genomics. I will discuss fundamental problems of model identifiability (degeneracy in model parameters that fit the data), interpretability (mapping discovered emergent variables back to neuron and gene circuits), and predictive power, and how geometry-aware deep learning models ameliorate these problems to enable new discoveries. Finally, I will describe some of the discoveries that we have made using this method about how the neural code is structured and used to accurately represent and efficiently search mental models of the world in mice learning to navigate a maze.

Bio: I am interested in discovering and modeling how articulate and intelligent biological function emerges from simpler parts. My undergraduate degree was in Biomedical Engineering at Duke University, where I did single-unit recordings in behaving macaques under electromagnetic stimulation. I did my graduate work in Bioengineering at the University of Pennsylvania designing articulate and intelligent biological function in mechanistic mathematical models ranging from cooperative energy landscapes in mechanical models of proteins, to mental simulation of video games in dynamical models of the brain. I am currently a postdoctoral fellow in Theoretical Physics, Neurotech, and AI for Science at Cornell University developing novel techniques to discover quantitative, interpretable, and predictive models of the algorithms that brains use to navigate physical and conceptual spaces, and cells use to produce life.

Date: Thursday, February 19, 2026 at 11:00 am

Location: Coda Building, Room 230 (Google Maps link)

Link: The recording of this in-person seminar will be uploaded to CSE's MediaSpace

Coffee and snacks provided!

Title: Towards a Less Conservative Theory of Machine Learning: Unstable Optimization and Implicit Regularization

Abstract: Deep learning’s empirical success challenges the “conservative" nature of classical optimization and statistical learning theories. Classical theory mandates small stepsizes for training stability and explicit regularization for complexity control. Yet, deep learning leverages mechanisms that thrive beyond these traditional boundaries. In this talk, I present a research program dedicated to building a less conservative theoretical foundation by demystifying two such mechanisms: 

1. Unstable Optimization: I show that large stepsizes, despite causing local oscillations, accelerate the global convergence of gradient descent (GD) in overparameterized logistic regression. 

2. Implicit Regularization: I show that the implicit regularization of early-stopped GD statistically dominates explicit $\ell_2$-regularization across all linear regression problem instances.

I further showcase how the theoretical principles lead to practice-relevant algorithmic designs (such as Seesaw for reducing serial steps in large language model pretraining). I conclude by outlining a path towards a rigorous understanding of modern learning paradigms.

Bio: Jingfeng Wu is a postdoctoral fellow at the Simons Institute for the Theory of Computing at UC Berkeley. His research focuses on deep learning theory, optimization, and statistical learning. He earned his Ph.D. in Computer Science from Johns Hopkins University in 2023. Prior to that, he received a B.S. in Mathematics (2016) and an M.S. in Applied Mathematics (2019), both from Peking University.

Date: Thursday, February 5, 2026 at 11:00 am

Location: Coda Building, Room 114 (Google Maps link)

Link: The recording of this in-person seminar will be uploaded to CSE's MediaSpace

Coffee and snacks provided!

Title: Designing Dynamic Measure Transport for Density-Driven Sampling

Abstract: Sampling from a target probability distribution is fundamental to modern computational science and machine learning. Sampling is the essence of Monte Carlo integration, enables uncertainty quantification in Bayesian inference, and underlies generative models that have the ability to synthesize convincing text, images, and far beyond. A powerful, emerging approach to sampling is dynamic measure transport (DMT): the idea is to design an ordinary or stochastic differential equation that evolves samples from a tractable reference distribution (e.g., a Gaussian) to the desired target distribution. DMT is state-of-the-art in generative modeling and underlies techniques such as diffusion models and flow-matching, but DMT pipelines for density-driven sampling tasks, as arising in computational chemistry and Bayesian inference, are significantly less developed. In this talk, I will discuss my work to make density-driven DMT a reality via: (1) development of new, gradient-free particle systems for Bayesian sampling, (2) principled design of DMT via PDE-constrained optimization, and (3) scalability through the exploitation of sparse conditional dependence structure. I will describe how these efforts will enable new DMT approaches to complex sampling problems--such as ensemble data assimilation, in which the prior is only known through samples---and sketch future work on stochastic inverse problems, in which an unknown distribution must be recovered from indirect measurements.

Bio: Aimee Maurais is in the final year of her Computational Science and Engineering Ph.D. at MIT. Prior to beginning her graduate work, Aimee earned bachelor’s degrees in Mathematics and Computational Modeling and Data Analytics from Virginia Tech and spent 1.5 years on the technical staff at MIT Lincoln Laboratory. In her research, Aimee makes use of geometry and structure to develop principled computational methods for probabilistic modeling and inference, and her current focus is on dynamic measure transport for sampling. Aimee’s work is supported by fellowships from the National Science Foundation and Google.

Bio: Robert Stuart-Smith is Founding Director of the Master of Science in Design: Robotics and Autonomous Systems (MSD-RAS) program, Assistant Professor of Architecture, and an affiliate faculty member in the Engineering School’s GRASP Laboratory at the University of Pennsylvania (Penn). He is also a Principal Research Associate in University College London’s (UCL) Department of Computer Science. Stuart-Smith leads the Autonomous Manufacturing Lab across Penn and UCL, where he has secured over $6.9M in competitive research funding and collaborates with industry partners including Cemex, Skanska, Mace, Buro Happold, Arup, and the Manufacturing Technology Centre (MTC). Stuart-Smith’s research focuses on robotics-enabled fabrication and construction systems, adaptive multi-robot processes, and integrated AI-driven generative design workflows. His Aerial Additive Manufacturing research —published in Nature—introduced in-flight additive manufacturing using coordinated aerial robotic agents. Stuart-Smith’s work has also been published in Science Robotics, AD Architectural Design, and L’Architecture d’Aujourd’hui, and featured by outlets including BBC Click, New Scientist, Smithsonian, and Architizer.

Abstract: Gradient-based data attribution methods, such as influence functions, are critical for understanding the impact of individual training samples without repeated model retraining. However, their scalability is often limited by the high computational and memory costs associated with per-sample gradient computation, especially for large-scale models and datasets. In this talk, I will present our recent work on scalable influence function computation through sparse gradient compression and projection techniques with provable guarantees. I will also discuss how these methods can be applied to real-world scenarios, such as online reinforcement learning where data filtering interacts with policy learning.

Bio: Dr. Han Zhao is an Assistant Professor of Computer Science at the University of Illinois Urbana-Champaign (UIUC). He is also an Amazon Scholar at Amazon AI. Dr. Zhao earned his Ph.D. degree in machine learning from Carnegie Mellon University. His research interest is centered around trustworthy machine learning, with a focus on algorithmic fairness, robust generalization and data interpretability. He has been named a Kavli Fellow of the National Academy of Sciences. His research has been recognized through an NSF CAREER Award, a Google Research Scholar Award, an Amazon Research Award, and a Meta Research Award.

For more information, or for CODA guest access, please contact shatcher8@gatech.edu at least 2 business days prior to the event.

Join Via Zoom: https://gatech.zoom.us/j/98188267850?pwd=SOTPAZaZm0qkaiGxezfwMFaIbP1eeI.1
Meeting ID: 981 8826 7850 
Passcode: 520805

Beginning with underwater vehicles and distributed control for multi-agent coordination, the talk will trace the evolution of my work through ground and aerial robotics, where nonlinear and robust control methods were developed to enable agility, adaptability, and resilience. The discussion will then move into human-centered robotics, including humanoid platforms, rehabilitation robotics, and powered exoskeletons designed to restore or augment human movement. These efforts have increasingly blurred the boundaries between machine and human, culminating in recent work on physical human-machine interaction and assistive technologies that embody both engineering rigor and social impact.

Drawing from experiences in academia, government, and interdisciplinary collaboration, the presentation will offer an integrated perspective on how robotic systems can enhance human capability, extend our reach into extreme environments, and inspire the next generation of engineers and explorers.

Bio: Dr. Alexander Leonessa is the Chair of the Department of Mechanical Engineering at Clemson University, where he also holds the D.W. Reynolds Distinguished Professorship. His career spans more than twenty-five years of research, teaching, and leadership in robotics, control systems, and human–machine interaction.

Before joining Clemson, Dr. Leonessa served as a Program Director at the National Science Foundation, where he led the Mind, Machine, Motor Nexus (M3X) program and oversaw the Foundational Research in Robotics (FRR) and the Dynamic, Control and Systems Diagnostics (DCSD) programs. In that role, he managed a research portfolio of approximately $10 million, advancing national efforts in robotics, assistive technologies, and neuroengineering.

Dr. Leonessa’s research has explored robotic systems across domains — underwater, ground, aerial, and humanoid — integrating robust and nonlinear control theory with mechanical design and human-centered applications. His work in rehabilitation robotics, exoskeletons, and brain–computer interfaces has aimed to enhance mobility and restore function for individuals with physical impairments, while his contributions to autonomous systems have influenced applications ranging from marine exploration to precision agriculture and planetary mobility.

He has published more than one hundred peer-reviewed papers, authored a book on nonlinear switching control, and secured over twenty-six million dollars in research funding from agencies including NSF, ONR, DARPA, and the Department of Agriculture. He has advised more than fifty graduate students and received multiple honors, including the NSF CAREER Award, Virginia Tech’s Alumni Award for Outreach Excellence, and the Dean’s Award for Outstanding New Assistant Professor.

Dr. Leonessa earned his B.S. in Aeronautical Engineering from the University of Rome “La Sapienza” and his M.S. and Ph.D. degrees in Aerospace Engineering from the Georgia Institute of Technology.

 1 p.m. "Modernizing C4G BLIS: The Road to BLIS 4.0"

Mitchell Rysavy (Senior Software Engineer, Microsoft)

 1:30 p.m."Computing for Good in an Increasingly Bad World"

Michael Best (Professor, School of International Affairs and School of Interactive Computing, Georgia Tech)

 2 p.m. "Disaster Response in Rural Communities"

Justin McLellan (Software Engineering Manager, Crexi)

 2:30 p.m. "HandS together: Innovation and Collaboration for Greater Impact"

Protip Biswas (Vice President, United Way Regional Commission on Homelessness)

Bio: Kostas’ research interests are in computer vision and robotic perception. His research addresses challenges in the perception of motion and space, such as the geometric design of cameras, and the interplay of geometry and appearance in perception tasks. Kostas’s research gives solutions to perceptual tasks such as panoramic vision, localization, perception of self-motion, large-scale mapping, visual location recognition, 3-D object recognition, and vision-based flocking. Applications of his research involve robot navigation, tele-immersion, and image and shape retrieval.

Title: Learning World Models and Agents for High-Cost Environments

Abstract: While neural networks have achieved superhuman performance in domains with low-cost simulations—from AlphaGo to LLMs—their application to the physical world is bottlenecked by a fundamental challenge: high-cost interactions. In fields like robotics, ML engineering, and the natural sciences, every action or experiment is expensive and time-consuming. This talk outlines strategies for building intelligent agents that learn efficiently despite these real-world constraints. We first address the physical world by showing how learned world models can serve as high-fidelity simulators for robotics, enabling extensive policy refinement before deployment on costly hardware. We then turn to complex engineering domains, where actions like running an ML program incur significant time delays, and discuss adaptations to reinforcement learning to make it robust for these long action settings. Finally, we show how compositional generative models can navigate the vast hypothesis spaces in science, intelligently proposing experiments to accelerate the pace of discovery.

Bio: Sherry Yang is an Assistant Professor of Computer Science at NYU Courant and a Staff Research Scientist at Google DeepMind. She researches in machine learning with a focus on reinforcement learning and generative modeling. Her current research interests include learning world models and agents, and their applications in robotics and AI for science. Her research has been recognized by the Best Paper award at ICLR and various media outlets such as VentureBeat and TWIML. She has organized tutorials, workshops, and served as Area Chairs at major conferences (NeurIPS, ICLR, ICML, CVPR). Prior to her current role, she was a post-doc at Stanford working with Percy Liang. She received her Ph.D. from UC Berkeley advised by Pieter Abbeel and master’s and bachelor's degrees from MIT.

Program Courses:

• CS 4001 – Computing & Society (Ethics Credit) - Students will critically examine how issues around technology such as globalization, bias, privacy, and others affect people worldwide.

• CS 3751 – Intro to User Interface Design - Students will explore culturally situated approaches to design and, through the course project, create an inventive design artifact.

Applications are now open HERE. Email indiaprogram@cc.gatech.edu for questions and to find out more about upcoming Info Sessions.

Agenda

• Research overview
• Commercialization updates
• Q&A session

Held in the Clary Theater in the Bill More Student Success Center or virtually via Zoom.

Title: Accelerating Fundamental Physics Research with AI: From Designing Theories to Testing Them in Experiments

Abstract: In fundamental physics, we build bottom-up theories to explain the universe from elementary particles to the nature of gravity. Theoretical advancements have traditionally relied on human insight into complex mathematics without a systematic way to explore ideas. I will talk about an emerging research direction in neuro-symbolic AI to systematize this exploration and discuss challenges in scaling this approach.

Once you have a set of interesting theories, testing them in experiments, such as at the Large Hadron Collider, is yet another computational and engineering challenge. High-dimensional data are generated at 50 MHz (40 TB/s), and we need to make decisions using efficient hardware. I will also discuss how neural inference techniques let us maximally use the high-dimensional data and current efforts to make these algorithms compute-efficient.

Bio: Aishik Ghosh is an assistant professor in the School of Physics at Georgia Tech with a focus on developing AI methods to accelerate fundamental physics and astrophysics. His group works on theoretical physics, statistical methods, and experiment design. For robust scientific applications, Dr. Ghosh focuses on uncertainty quantification, interpretability, and verifiability of AI algorithms, targeting publications in physics journals and ML conferences.

Program Courses:

• CS 4001 – Computing & Society (Ethics Credit) - Students will critically examine how issues around technology such as globalization, bias, privacy, and others affect people worldwide.

• CS 3751 – Intro to User Interface Design - Students will explore culturally situated approaches to design and, through the course project, create an inventive design artifact.

Applications are now open HERE. Email indiaprogram@cc.gatech.edu for questions and to find out more about upcoming Info Sessions.

Title: Generative Artificial Intelligence for Uncertainty Quantification

Abstract: Generative artificial intelligence models, including variational autoencoders, normalizing flows, generative adversarial networks, and diffusion models, have dramatically advanced the realism and quality of generated images, text, and audio. Beyond media synthesis, these models hold great promise as powerful tools for probability density estimation and high-dimensional sampling, which are central to uncertainty quantification (UQ) tasks such as amortized Bayesian inference and data assimilation. However, while research on image and audio synthesis emphasizes producing high-quality individual samples, UQ applications demand accurate approximation of statistical quantities of interest rather than visually realistic samples. As a result, direct application of existing generative models to UQ problems can lead to biased approximations or unstable training. In this talk, I will introduce several new generative approaches tailored to UQ. These include training-free diffusion models for density estimation, a score-based nonlinear filter for data assimilation, and conditional diffusion models for amortized Bayesian inference. I will demonstrate their effectiveness across a range of tasks, including density estimation for unimodal and multimodal distributions, learning stochastic dynamical systems, parameter estimation via amortized inference, and scalable data assimilation for atmospheric models.

Bio: Dr. Guannan Zhang is a Distinguished Staff Scientist in Computer Science and Mathematics Division at Oak Ridge National Laboratory (ORNL). He earned my Ph.D. in applied mathematics at Florida State University in 2012. He joined ORNL in 2012 as the Householder fellow. He received the DOE Early Career Award in 2022. He has been holding a joint faculty appointment with the Department of Mathematics and Statistics at Auburn University since 2014, and a joint faculty appointment with Department of Mathematics at University of Tennessee since 2022. Guannan's research interests include high-dimensional approximation, uncertainty quantification, machine learning and artificial intelligence, stochastic methods for scientific inverse problems. 

We invite you to study abroad this summer with the College of Computing! Take 12 GT credit hours while immersing yourself in the exciting environments of Barcelona. See below for information on program details and application info.

2026 Barcelona Summer Program course offerings include:

• CS 2050 – Intro to Discrete Math for CS
• CS 3750 – Human-Computer Interface Design & Evaluation
• CS 4001 – Computing and Society (Ethics credit)
• CS 4400 – Intro to Database Systems
• CS 4660 – Intro to Educational Technology
• CS 4726 – Privacy, Technology, Policy, & Law (Ethics Credit)
• CS 4803-EDG – Educational Game Design
• ARCH 3135 – City Literacy: What Makes Great Cities Great (Social Sciences Credit)

Review the attached flyer and email barcelona@cc.gatech.edu for questions. Application deadline: December 1st in Atlas.

We invite you to study abroad this summer with the College of Computing! Take 12 GT credit hours while immersing yourself in the exciting environments of Berlin. See below for information on program details and application info.

2026 Berlin Summer Program course offerings include:

• CS 2340 – Objects & Design
• CS 2701 – Startup Lab
• CS 3510 – Algorithm Design
• CS 3600 - Intro to Artificial Intelligence
• CS 4001 – Computing and Society (Ethics credit)
• CS 4400 – Intro to Database Systems
• LMC 3262 – Performance Studies (Humanities credit)
• LMC 3314 – Technologies of Representation (Humanities credit)

Berlin is a growing Tech Hub in Europe, home to innovative companies and research institutions, and host to tech meetups, hackathons, and conferences. With focus on entrepreneurship and start-up culture, this program is a great option if you are a CM major, if your CS Threads are Intelligence or Information-Internetworks, or if you’re doing the Create-X: Idea-To-Protype Junior Design option.

Review the attached flyer and email berlin@cc.gatech.edu for questions. Application deadline: December 1st in Atlas.