You are cordially invited to attend the biweekly Brookhaven AI Mixer (BAM). BAM includes three short talks on AI research happening at BNL, followed by an open mixer over coffee and snacks for everyone to network and discuss all things AI. The first half hour will consist of presentations that will be available via ZOOM, and the second half hour will be for in person only networking.

Join us every other Tuesday at noon in CDSD's Training Room (building 725, 2nd floor) to learn about interesting AI methods and applications, engage with potential collaborators, prepare for pending FASST funding calls, and build a community of AI for Science at BNL.

Tuesday, January 7, 2025, 12:00 pm -- CDS, Bldg. 725, Training Room

Speakers

Jianda Chen, EBNN - Improving the stability and accuracy of PDE-ML hybrid AGCMs

Boyang Li, CDS - Accelerating Materials Discovery using Machine Learning

Jaehye on Do, NPP Isotopes - Using LLMs for Isotopes Research and Production

Join ZoomGov Meeting: https://bnl.zoomgov.com/j/1615289117?pwd=Hqkbj9itxWrFnkhZ8rQXHPInO2gxdF.1

Meeting ID: 161 528 9117
Passcode: 991382

Abstract: Recent studies have highlighted the vulnerability of Natural Language Processing (NLP) and Vision-Language Models (VLMs) to backdoor attacks, posing significant security risks. Understanding these attack strategies is crucial for assessing model robustness and developing effective defenses. This thesis proposal aims to investigate the vulnerability of language and vision-language models, analyze abnormal behaviors in backdoor-attacked models, and develop defense methods to enhance safety of modern machine learning models at deployment.


We investigate the internal mechanisms of backdoored NLP models, identifying a distinct attention focus drifting phenomenon, where trigger tokens hijack attention regardless of the input context. Through comprehensive qualitative and quantitative analysis, we provide insights into the underlying mechanisms that enable backdoor attacks. Building on these insights, we propose detection methods to differentiate backdoored models from clean ones, through inspecting both the attention distribution and the model predictions. To better understand the vulnerability, we develop advanced backdoor attack strategies targeting language models in classification tasks. For BERT variants, we introduce Trojan Attention Loss (TAL), a novel method that directly manipulates attention patterns to enhance backdoor effectiveness, ensuring stealth and robustness. Vision-Language Models have demonstrated strong performance in recent years. Yet their vulnerability is largely underexplored. We investigate advanced backdoor attack strategies on Vision-Language Models, focusing on image-to-text generation tasks. We demonstrate how backdoors can be embedded in complex multimodal tasks while maintaining semantic integrity under poisoned inputs. Additionally, we propose innovative techniques for injecting backdoors without requiring access to the original training data, expanding the feasibility of real-world attacks.

This proposal provides novel insights into the internal mechanisms of backdoored models, propose effective detection strategies, and develop advanced attack techniques that expose critical vulnerabilities. These findings underscore the urgent need for robust security measures to defend against emerging backdoor threats in deep learning models. The results have been published in top venues including ICLR, ECCV, NAACL, EMNLP, etc.

Speaker: Weimin Lyu


Zoom link: https://stonybrook.zoom.us/j/99880605139?pwd=cfWbRG6n9v3GXEa7OqvXa5cOp5eLBv.1
Meeting ID: 998 8060 5139
Passcode: 843302
TITLE: Sampling Using Langevin Diffusions Beyond the Worst-Case by Andrej Risteski of CMU


ABSTRACT: Many tasks involving generative models involve being able to sample from distributions parametrized as p(x) = e^{-f(x)}/Z where Z is the normalizing constant, for some function f whose values and gradients we can query. This mode of access to f is natural -- for instance sampling from posteriors in latent-variable models. Classical results show that a natural random walk, Langevin diffusion, mixes rapidly when f is convex. Unfortunately, even in simple examples, the applications listed above will entail working with functions f that are nonconvex.

We exhibit instances where Langevin diffusion (combined with other tools) can provably be shown to mix rapidly in instances of relevance in practice: distributions p that are multimodal, as well as distributions p that have a natural manifold structure on their level sets. 










Abstract:
Quantifying similarity is a central notion in science and data analysis, pervading everything from phylogenetic trees to the foundation of clustering. Unfortunately, despite being examined and applied for decades, traditional similarity and distance metrics have fundamental drawbacks. The key problem is that all of them are only defined over pairs of objects, so they scale quadratically when one tries to compare N objects. The present explosion in the amount of data available to us requires new ways to process information, and while some current algorithms can handle millions of points, we need alternatives applicable to billions. This is what motivated us to develop a new framework that can compare any number of objects at the same time. With this, we achieve an unprecedented linear scaling when comparing multiple objects. Here we will discuss the main properties of this formalism, along with its applications in drug design and to the analysis of Molecular Dynamics (MD) simulations. Our indices have proven to be incredibly versatile when applied to chemical space exploration and visualization, allowing us to rigorously quantify the chemical diversity of very large molecular libraries. This has led to the creation of several algorithms to sample important regions in chemical space, including a more efficient way of identifying the prevalence of activity cliffs. Additionally, our indices provide a convenient route to sample complex MD trajectories, allowing to identify representative structures very efficiently. Moreover, we can also cluster biological ensembles in a more robust way than with standard algorithms, which has led to our group's work on MDANCE, a very flexible and efficient open-source clustering module. Drop by if you want to know how we clustered one billion molecules!


Speaker:
Assistant Professor, Department of Chemistry and Quantum Theory Project
University of Florida, Gainesville
Website: https://quintana.chem.ufl.edu/

Location:
Laufer Center Lecture Hall 101

Imagine machines that can see beyond human limitations--drones locating hidden survivors, cameras predicting structural failures, or medical devices detecting tumors beneath the skin. Traditional vision systems are constrained by the boundaries of human perception, missing vast information present in light interactions. This talk explores the development of advanced vision systems that capture underutilized dimensions of light, model intricate light-scene interactions, and extract hidden 3D information--around corners, beneath surfaces, and at high speeds. By jointly developing novel imaging hardware, efficient rendering models, and physics-based learning algorithms, we aim to transcend conventional vision capabilities--unlocking critical applications in autonomous navigation, structural monitoring, and non-invasive medical imaging.

Speaker Bio:


Akshat Dave is a Postdoctoral Associate at MIT Media Lab in the Camera Culture group working with Prof. Ramesh Raskar. He received his Ph.D. from Rice University ECE Department in 2023 where he was advised by Prof. Ashok Veeraraghavan. His research lies at the intersection of applied optics, computer graphics, and computer vision. His research focuses on developing vision systems that go beyond human perception. His work has been recognized by Rice University's Best Thesis Award, OSA Best Paper Prize, and fellowships by Texas Instruments and Qualcomm.

Please join us this Friday, February 13th for the CSE 600 seminar given by Associate Professor Debswapna Bhattacharya, from the Department of Computer Science at Virginia Tech.

Abstract: Building a model of a biological system that can provide actionable hypotheses to form a solid foundation for experimental and theoretical analyses is one of the key challenges in biology and medicine. In this talk, I will present my group's ongoing work in developing, evaluating, and disseminating a new generation of computational methods for biomolecular modeling powered by artificial intelligence (AI) and machine learning (ML). First, I will introduce a new generation of AI/ML methods for improved modeling and characterization of protein-nucleic acid assemblies by deep graph learning using embeddings from biological large language models (LLMs) as well as geometric attention-enabled pairing of heterogeneous biological LLMs, a previously unexplored avenue. Then, I will present a novel generative deep learning model based on equivariant flow matching for end-to-end generation of all-atom RNA 3D structural ensemble. Finally, I will outline my future research directions on attaining atomic-level accuracy in computational modeling of biomolecules and their assemblies at scale.

Speaker: Debswapna Bhattacharya is an Associate Professor in the Department of Computer Science at Virginia Tech. He received his Ph.D. in Computer Science from the University of Missouri-Columbia in 2016. Before joining Virginia Tech in 2022, he was an Assistant Professor at Auburn University from 2017 to 2021. His research interests lie at the intersection of computational biology and machine learning, with a particular focus on artificial intelligence for computational structural biology, specifically in modeling and characterization of biomolecular structures and interactions. His research group has been developing novel computational and data-driven methods, software, and information systems for diverse biomolecular modeling problems, ranking among the best methods in community-wide blind assessments and serving the worldwide community of biomedical users. He received various research awards (NSF CAREER Award, NIH Maximizing Investigators' Research Award, NSF National AI Research Resource Award) and numerous institutional honors (National Distinction and Outstanding Contributor at Virginia Tech, Ginn Faculty Fellowship at Auburn University, Outstanding Engineering Faculty Award at Auburn University).
Location: NCS 120

Learn how to summarize docs with AI, output a PowerPoint from AI, & Create professional visuals

Unlock greater efficiency and impact in your university role with AI productivity tools. This workshop is your introduction to a few ways that I have found to make our daily tasks more efficient. Discover how easily you can create presentations (that outputs to a PowerPoint format), summarize content using AI, and get information from images. These AI tool tips are invaluable resources designed to streamline your work processes. Start working smarter today!

In this session, you will

  1. Summarize docs with AI
  2. Output a PowerPoint from AI
  3. Gather information from visuals

Register here.

The event will take place on Zoom and will feature two distinguished guest speakers: SBU alumnus, Velchamy Sankarlingam, president of Product and Engineering at Zoom, and Simeon Ananou, vice president for Information Technology and CIO at Stony Brook University. The discussion will be moderated by Haresh Gurnani, dean of the College of Business at Stony Brook University.

Exploring AI's Impact on Communication and Connection

Artificial Intelligence (AI) has rapidly evolved, becoming an integral part of various industries, including education and business. This event aims to delve into how AI is reshaping the way we learn and work, particularly in enhancing communication and fostering human connections. Velchamy Sankarlingam, an SBU alumnus and a key figure at Zoom, will share his insights on how AI-driven tools are revolutionizing virtual communication platforms, making interactions more seamless and effective.

Simeon Ananou, with his extensive experience in information technology, will provide a perspective on how AI is being integrated into educational institutions to improve learning outcomes and administrative efficiency. His role at Stony Brook University places him at the forefront of implementing innovative technologies that benefit both students and staff.

A Conversation Led by Expertise

Dean Haresh Gurnani, known for his leadership and expertise in business education, will guide the conversation, ensuring that the discussion remains focused on the practical implications of AI. He will explore how AI is not only boosting productivity but also enriching overall experiences in the workplace and educational settings. The event will include an interactive Q&A session, allowing attendees to engage directly with the speakers and gain deeper insights into the topics discussed.

As AI continues to develop, events like this are crucial for understanding its impact and potential. Stony Brook University's College of Business is committed to providing platforms for such important discussions, fostering an environment where innovation and education intersect.

This event is open to all. Please visit https://www.givecampus.com/schools/StonyBrookUniversity/events/artificial-intelligence-reshaping-learning-and-work to register.