The GE Vernova Advanced Research Center invites you to the 2026 AI EDGE Symposium.

This collaborative and hands-on learning experience connects 300+ industry thought leaders in the fields of AI, Edge, Robotics, Cybersecurity, and Controls & Optimization.


Attendees will learn about the latest challenges and innovations with luminaries from key government agencies, industry customers, and technology partners as they discuss the latest advancements and trends in these fields.

Register here.

Abstract: My presentation will be focused on introducing the use of Screenomics, a passive sensing approach that directly collects time-intensive data from participants' smartphones, to observe and analyze adolescents' digital behaviors across multiple timescales. I will present our completed and ongoing efforts using Screenomics to (1) evaluate the biases of self-reports of screen time and app use, (2) describe how adolescents use their smartphones during school hours and overnight, (3) examine longitudinal associations between adolescents' social media use and mental health, and (4) capture adolescents' communication pattern with parents. I will also introduce the theoretical framework and study plan for a new NIH-funded project that aims to identify adolescents' social media management strategies (SMMS) and how SMMS are related to adolescents' actual social media use and mental health. I will conclude with a discussion of future directions for interventions to promote healthy digital practices among adolescents.

Bio: Xiaoran Sun, Ph.D., is an assistant professor in the Department of Family Social Science, College of Education and Human Development at University of Minnesota (UMN). She is the director of the UMN Technology, Teens, and Families Lab and a core faculty of the Learning Informatics Lab. She is also affiliated with the UMN Data Science Initiative and the Minnesota Population Center. Her research is mainly focused on using innovative approaches, such as passive sensing and machine learning, to examine children's and parents' use of technology and the implications for their wellbeing. Her work is being funded by the U.S. National Institute of Mental Health and the Spencer Foundation.

Abstract: Many unresolved legal questions over LLMs and copyright center on memorization: whether specific training data have been encoded in the model's weights during training, and whether those memorized data can be extracted in the model's outputs. While many believe that LLMs do not memorize much of their training data, recent work shows that substantial amounts of copyrighted text can be extracted from open-weight models. However, it remains an open question if similar extraction is feasible for production LLMs, given the safety measures these systems implement. We investigate this question using a two-phase procedure: (1) an initial probe to test for extraction feasibility, which sometimes uses a Best-of-N (BoN) jailbreak, followed by (2) iterative continuation prompts to attempt to extract the book. We evaluate our procedure on four production LLMs -- Claude 3.7 Sonnet, GPT-4.1, Gemini 2.5 Pro, and Grok 3 -- and we measure extraction success with a score computed from a block-based approximation of longest common substring (nv-recall). With different per-LLM experimental configurations, we were able to extract varying amounts of text. For the Phase 1 probe, it was unnecessary to jailbreak Gemini 2.5 Pro and Grok 3 to extract text (e.g, nv-recall of 76.8% and 70.3%, respectively, for Harry Potter and the Sorcerer's Stone), while it was necessary for Claude 3.7 Sonnet and GPT-4.1. In some cases, jailbroken Claude 3.7 Sonnet outputs entire books near-verbatim (e.g., nv-recall=95.8%). GPT-4.1 requires significantly more BoN attempts (e.g., 20X), and eventually refuses to continue (e.g., nv-recall=4.0%). Taken together, our work highlights that, even with model- and system-level safeguards, extraction of (in-copyright) training data remains a risk for production LLMs.

Speaker: Xinyue

Location: CS2311
The overall purpose of this seminar is to bring together people with interests in Computer Vision theory and techniques and to examine current research issues. This course will be appropriate for people who already took a Computer Vision graduate course or already had research experience in Computer Vision. To enroll in this course, you must either: (1) be in the PhD program or (2) receive permission from the instructors.

Each seminar will consist of multiple short talks (around 10 minutes) by multiple people. Students can register for 1 credit for CSE 656. Registered students must attend and present a minimum of 2 or 3 talks. Everyone else is welcome to attend. Fill in https://forms.gle/pCVXovgfMfQwGqG38 to subscribe to our mailing list for further announcement.

The next AI Institute seminar speaker will be Chao Chen of Biomedical Informatics, on Monday November 29 at noon via zoom:

https://stonybrook.zoom.us/j/96233844681?pwd=aVVsUnIzMWJDMHRqVXcrQU5HMjFVQT09

He will be talking on the Detection of Trojan Attacks to Deep Neural Networks - A Topological Perspective, with his abstract and bio below.


Abstract: Deep neural networks are known to have security issues. One particular threat is the Trojan attack. It occurs when the attackers stealthily manipulate the model's behavior through Trojaned training samples, i.e., samples with special trigger injected and labels altered. To identify a Trojaned model at deployment is challenging, due to limited access to the training data. We propose to identify Trojaned neural networks using methods from topological data analysis. In particular, we propose to (1) inspect high-order topological features of the neuron interactions and (2) reverse engineer the injected triggers using a topological loss. These approaches take different angles and reveal insights into the behavior of neural networks when their strong memorialization power is exploited maliciously. The work has been accepted to NeurIPS'21. I will also briefly mention other research directions from my group, including incorporating topological information into deep image analysis, topology-inspired graph neural networks, and robust training of neural networks with label noise. These works have been published in ICLR, ICML, NeurIPS, ECCV, ICCV and AAAI in recent years.
Bio: Dr. Chao Chen is an assistant professor of Biomedical Informatics at Stony Brook University. His research interests span topological data analysis (TDA), machine learning and biomedical image analysis. He develops principled learning methods inspired by the theory from TDA, such as persistent homology and discrete Morse theory. These methods address problems in biomedical image analysis, robust machine learning, and graph neural networks from a unique topological view. His research results have been published in major machine learning, computer vision, and medical image analysis conferences. He is serving as an area chair for MICCAI, AAAI, CVPR and NeurIPS.