Join virtually for a candid discussion with Joel Pendleton (Conductor Quantum) on real-world opportunities, technical constraints, and emerging risks at the intersection of quantum and AI.
The 39th Annual AAAI Conference on Artificial Intelligence will be held from February 25 to March 4, 2025 in Philadelphia, Pennsylvania, USA. More information can be found here.
Postmortem Program Analysis from a Conventional Program Analysis Method to an AI-assisted Approach
Abstract: Despite the best efforts of developers, software inevitably contains flaws that may be leveraged as security vulnerabilities. Modern operating systems integrate various security mechanisms to prevent software faults from being exploited. To bypass these defenses and hijack program execution, an attacker needs to constantly mutate an exploit and make many attempts. While in their attempts, the exploit triggers a security vulnerability and makes the running process abnormally terminate.
After a program has crashed and abnormally terminated, it typically leaves behind a snapshot of its crashing state in the form of a core dump. While a core dump carries a large amount of information, which has long been used for software debugging, it barely serves as informative debugging aids in locating software faults, particularly memory corruption vulnerabilities. As such, previous research mainly seeks fully reproducible execution tracing to identify software vulnerabilities in crashes. However, such techniques are usually impractical for complex programs. Even for simple programs, the overhead of fully reproducible tracing may only be acceptable at the time of in-house testing.
In this talk, I will discuss how we tackle this issue by bridging program analysis with artificial intelligence (AI). More specifically, I will first talk about the history of postmortem program analysis, characterizing and disclosing their limitations. Second, I will introduce how we design a new reverse-execution approach for postmortem program analysis. Third, I will discuss how we integrate AI into our reverse-execution method to escalate its analysis efficiency and accuracy. Last but not least, as part of this talk, I will demonstrate the effectiveness of this AI-assisted postmortem program analysis framework by using massive amounts of real-world programs.
Bio: Dr. Xinyu Xing is an Assistant Professor at Pennsylvania State University. His research interests include exploring, designing and developing new program analysis and AI techniques to automate vulnerability discovery, failure reproduction, vulnerability diagnosis (and triage), exploit and security patch generation. His past research has been featured by many mainstream media and received the best paper awards from ACM CCS and ACSAC. Going beyond academic research, he also actively participates and hosts many world-class cybersecurity competitions (such as HITB and XCTF). As the founder of JD-OMEGA, his team has been selected for DEFCON/GeekPwn AI challenge grand final at Las Vegas. Currently, his research is mainly supported by NSF, ONR, NSA and industry partners.
Abstract: Despite the best efforts of developers, software inevitably contains flaws that may be leveraged as security vulnerabilities. Modern operating systems integrate various security mechanisms to prevent software faults from being exploited. To bypass these defenses and hijack program execution, an attacker needs to constantly mutate an exploit and make many attempts. While in their attempts, the exploit triggers a security vulnerability and makes the running process abnormally terminate.
After a program has crashed and abnormally terminated, it typically leaves behind a snapshot of its crashing state in the form of a core dump. While a core dump carries a large amount of information, which has long been used for software debugging, it barely serves as informative debugging aids in locating software faults, particularly memory corruption vulnerabilities. As such, previous research mainly seeks fully reproducible execution tracing to identify software vulnerabilities in crashes. However, such techniques are usually impractical for complex programs. Even for simple programs, the overhead of fully reproducible tracing may only be acceptable at the time of in-house testing.
In this talk, I will discuss how we tackle this issue by bridging program analysis with artificial intelligence (AI). More specifically, I will first talk about the history of postmortem program analysis, characterizing and disclosing their limitations. Second, I will introduce how we design a new reverse-execution approach for postmortem program analysis. Third, I will discuss how we integrate AI into our reverse-execution method to escalate its analysis efficiency and accuracy. Last but not least, as part of this talk, I will demonstrate the effectiveness of this AI-assisted postmortem program analysis framework by using massive amounts of real-world programs.
Bio: Dr. Xinyu Xing is an Assistant Professor at Pennsylvania State University. His research interests include exploring, designing and developing new program analysis and AI techniques to automate vulnerability discovery, failure reproduction, vulnerability diagnosis (and triage), exploit and security patch generation. His past research has been featured by many mainstream media and received the best paper awards from ACM CCS and ACSAC. Going beyond academic research, he also actively participates and hosts many world-class cybersecurity competitions (such as HITB and XCTF). As the founder of JD-OMEGA, his team has been selected for DEFCON/GeekPwn AI challenge grand final at Las Vegas. Currently, his research is mainly supported by NSF, ONR, NSA and industry partners.
STEM Speaker Series: Steve Skiena - Representing Knowledge through Word and Graph Embeddings
The AI Community at Stony Brook University is proud to announce Datathon 2026.
Dive into data analysis and AI/ML, and get ready to build something big. In this year's underwater-themed event, enjoy a weekend of data analysis, hacking, networking, fun activities, and minigames.
Whether you're a seasoned developer, data scientist, designer, or completely new to hacking, this event is your chance to collaborate, learn data science, and create something impactful with data and AI/ML.
What is Datathon?
AI Community's Datathon is the premier data science competition at Stony Brook University, bringing together students of all skill levels for a weekend of data exploration, analysis, and innovation. Just like a typical hackathon, you will be using your skills to build your dream project.
Unlike a regular hackathon, Datathon is focused on data science. You will be given a set of data to work with, analyze, and apply to your project. You can also find your own data to use. Your project will be presented to a panel of judges consisting of professors and industry professionals!
Who Can Participate
- Students of all skill levels and majors are welcome.
- Come with a team or find one at the event or on Discord.
- This event is open to SBU and non-SBU students.
* Non-SBU Undergraduate Students are ineligible to receive prizes
* You must be 18+ or older (Excludes minors who are active SBU students)
Location: SAC Ballroom B
Register here.
Abstract: Humans perceive the world through global structures such as parts, branches, and their spatial arrangement. Most deep learning models, however, operate mainly at the pixel level. This disconnect between local and global understanding limits interpretability and control. In this thesis, we explore topology as a mathematical framework for bridging local predictions and global structure in dense prediction and generation tasks. We first incorporate topological constraints into semantic segmentation to preserve anatomical relationships and improve multi-class consistency. We next develop structure-level uncertainty estimation, producing more interpretable and actionable measures of model error over branches and connections rather than isolated pixels. Then, we introduce a topology-guided diffusion framework for controllable image generation using structural attributes such as object count and connectivity. Finally, we extend image generation to the longitudinal task, where we aim to capture structural changes across timepoints. All these contributions together establish topology as a unifying interface for building dense prediction models that are structurally aware, interpretable, and controllable.
Speaker: Saumya Gupta
Location: NCS 220
Zoom: https://stonybrook.zoom.us/j/97950688136?pwd=NCa3XOsgIaMIsTVlQBQJ11n27NzL8s.1
Meeting ID: 979 5068 8136
Passcode: 941798
Speaker: Saumya Gupta
Location: NCS 220
Zoom: https://stonybrook.zoom.us/j/97950688136?pwd=NCa3XOsgIaMIsTVlQBQJ11n27NzL8s.1
Meeting ID: 979 5068 8136
Passcode: 941798
Abstract: Foundation models brought a paradigm shift on representation learning and the deep learning community. In my talk, I will examine the role of foundation models in medical imaging, focusing on their potential to unify diverse tasks through large-scale, generalist architectures. While these models achieve strong performance, their deployment in healthcare raises challenges related to data limitations, privacy, validation, and trust. We will also discuss domain-specific models for imaging, along with efficient adaptation techniques to adapt such models on domains that they have not been trained on. The presentation will also address key issues of reliability and interpretability, highlighting approaches like conformal prediction and counterfactual intervention to improve uncertainty estimation and model transparency. Overall, the talk will emphasize that despite their promise, foundation models require robust evaluation and trustworthy design to ensure safe and effective use in clinical settings.
Speaker: Maria Vakalopoulou is an assistant professor (MCF) in applied mathematics at CentraleSupelec, University Paris Saclay in France and the group leader of the biomathematics group of MICS Laboratory focusing on mathematical modeling in Life Sciences. She is affliated with Inria Saclay in France and Archimedes Unit in Greece. Her main research interest include the development of computational methods for image perception focusing on earth observation and medical applications. Before that, she was a postdoctoral student at CentraleSupelec, where she worked with Nikos Paragios. She completed her PhD at the Remote Sensing Laboratory at the School of Rural, Surveying and Geo-Informatics Engineering of the National Technical University of Athens under the supervision of Konstantinos Karantzalos.
Location: NCS 220
Speaker: Maria Vakalopoulou is an assistant professor (MCF) in applied mathematics at CentraleSupelec, University Paris Saclay in France and the group leader of the biomathematics group of MICS Laboratory focusing on mathematical modeling in Life Sciences. She is affliated with Inria Saclay in France and Archimedes Unit in Greece. Her main research interest include the development of computational methods for image perception focusing on earth observation and medical applications. Before that, she was a postdoctoral student at CentraleSupelec, where she worked with Nikos Paragios. She completed her PhD at the Remote Sensing Laboratory at the School of Rural, Surveying and Geo-Informatics Engineering of the National Technical University of Athens under the supervision of Konstantinos Karantzalos.
Location: NCS 220
Abstract: Capturing the spatio-temporal (4D) dynamics of humans has been a long standing research problem in computer vision and graphics. Synthesizing photorealistic human avatars has broad applications, ranging from immersive telepresence in AR/VR and the movie industry, to enriching the education and healthcare systems. Earlier approaches relied on hand-engineered models that use a small amount of data from one or more subjects. With the advent of neural networks, training on large datasets enhanced the output visual quality. Currently, the combination of neural networks with graphics techniques has achieved natural-looking human animation. However, most approaches are identity-specific, trained only on a single identity, and use only one modality.
In this dissertation, we address the problem of learning neural representations of humans in a holistic way. Given that the video data in the real world include multiple modalities (e.g., audio and video) and multiple identities, we develop multi-modal and multi-identity representations. First, we propose to reconstruct the 4D face geometry of humans by leveraging both audio and video information. In this way, the network produces accurate lip shapes and is robust to cases when either modality is insufficient. Next, we introduce a NeRF-based representation for audio-driven human face animation that achieves high-quality lip synchronization for cinematic content. Since humans communicate with their full body, combining body pose, hand gestures, and facial expressions, we extend the network to capture full-body human motion for multiple identities simultaneously. In order to better disentangle identity and non-identity specific information, we subsequently study non-linear interactions between latent factors of variation, and propose a specific multiplicative module. In this way, we learn a multi-identity NeRF that robustly animates human faces under novel expressions and achieves a significant decrease in the total training time. Similarly, we propose a multi-identity Gaussian splatting representation for human bodies, by constructing a high-order tensor. Assuming a low-rank structure, we learn a tensor decomposition that leads to a significant decrease in the total number of learnable parameters, as well as to a robust animation under novel poses. Last but not least, we propose to jointly synthesize audio and visual outputs from just text input. Given the recent rise of large language models, coupling text with natural-looking avatars can enhance the overall interaction between a human and an AI system.
Location: NCS 220 or Zoom
In this dissertation, we address the problem of learning neural representations of humans in a holistic way. Given that the video data in the real world include multiple modalities (e.g., audio and video) and multiple identities, we develop multi-modal and multi-identity representations. First, we propose to reconstruct the 4D face geometry of humans by leveraging both audio and video information. In this way, the network produces accurate lip shapes and is robust to cases when either modality is insufficient. Next, we introduce a NeRF-based representation for audio-driven human face animation that achieves high-quality lip synchronization for cinematic content. Since humans communicate with their full body, combining body pose, hand gestures, and facial expressions, we extend the network to capture full-body human motion for multiple identities simultaneously. In order to better disentangle identity and non-identity specific information, we subsequently study non-linear interactions between latent factors of variation, and propose a specific multiplicative module. In this way, we learn a multi-identity NeRF that robustly animates human faces under novel expressions and achieves a significant decrease in the total training time. Similarly, we propose a multi-identity Gaussian splatting representation for human bodies, by constructing a high-order tensor. Assuming a low-rank structure, we learn a tensor decomposition that leads to a significant decrease in the total number of learnable parameters, as well as to a robust animation under novel poses. Last but not least, we propose to jointly synthesize audio and visual outputs from just text input. Given the recent rise of large language models, coupling text with natural-looking avatars can enhance the overall interaction between a human and an AI system.
Location: NCS 220 or Zoom
Zoom: https://stonybrook.zoom.us/j/
Meeting ID: 97512368946
passcode: 045476
passcode: 045476
Jerome Liang, PhD
Professor of Radiology, Biomedical Engineering, Electric and Computer Engineering, and Computer Science
Co-Director of Research
Department of Radiology
Artificial intelligence, machine learning and computer-aided diagnosis in cancer Imaging
February 11, 2021
12:00pm - 1:00pm
Virtual Seminar - Zoom
https://stonybrook.zoom.us/j/
Meeting ID: 981 5562 9970
Passcode: 950410
Host:
Wei Zhao, PhD
Professor of Radiology and Biomedical Engineering
Educational Objectives
Upon completion, participants should be able to:
(1) Learn different medical image representations of cancer attributes, such as heterogeneity, high tendency to grow, etc.
(2) Learn how computer (machine) can be trained (or programmed) to recognize the image representations.
(3) Learn how artificial intelligence can drive the machine learning to maximize the performance of computer-aided diagnosis (CADx).
Disclosure Statement
In compliance with the ACCME Standards for Commercial Support, everyone who is in a position to control the content of an educational activity provided by the School of Medicine is expected to disclose to the audience any relevant financial relationships with any commercial interest that relates to the content of his/her presentation.
The speaker, Jerome Liang, PhD, the planners; and the CME provider have no relevant financial relationship with a commercial interest (defined as any entity producing, marketing, re-selling, or distributing health care goods or services consumed by, or used on, patients), that relates to the content that will be discussed in the educational activity.
CONTINUING MEDICAL EDUCATION CREDITS
The School of Medicine, State University of New York at Stony Brook, is accredited by the Accreditation Council for Continuing Medical Education to provide continuing medical education for physicians.
The School of Medicine, State University of New York at Stony Brook designates this live activity for a maximum of 1.0 AMA PRA Category 1 Credits™. Physicians should only claim credit commensurate with the extent of their participation in the activity.
Should you be logging in Zoom by using your tablet or mobile device, please be sure to add your Full Name and/or Email for CME credit.
Abstract: Much like other AI for Science domains, polymer design poses significant challenges. It requires grounding in empirical data and physical laws, precise handling of domain-specific structured representations, and compositional reasoning over multiple interacting constraints--all while working with limited data.
To address these limitations, we introduce PolyBench, a large-scale benchmark comprising over 125K polymer design and analysis tasks grounded in verified experimental and synthetic data. PolyBench includes tasks created from a wide range of data sources and presents diverse structural, property-driven, and synthesis-oriented reasoning problems. Tasks in PolyBench are organized from simple to complex analytical reasoning problems, enabling generalization tests and includes diagnostic probes to evaluate model capabilities. Additionally, to support effective domain alignment, we propose a knowledge-augmented reasoning distillation framework that enriches the dataset with structured chain-of-thought supervision derived from expert-informed reasoning strategies.
Small language models (7B-14B parameters) trained on PolyBench substantially outperform comparably sized baselines and, in many cases, exceed the performance of larger closed-source frontier models on polymer reasoning tasks, while also demonstrating improved transfer to external polymer benchmarks. Last, we conduct a diagnostic study that reveals a compositionality gap: despite strong performance on decomposed sub-questions, models struggle to integrate multiple interacting constraints and intermediate reasoning steps, highlighting fundamental limitations in current scientific language models.
Speaker: Dikshya Mohanty
Location: NCS 115/Online
Zoom: https://stonybrook.zoom.
Meeting ID: 947 4600 1760 Passcode: 987917