Abstract: Gaussian Probability Path-based Generative Models (GPPGMs) generate data by reversing a stochastic process that progressively corrupts samples with Gaussian noise. Despite state-of-the-art results in 3D molecular generation, their deployment is hindered by the high cost of long generative trajectories, often requiring hundreds to thousands of steps during training and sampling. In this work, we propose a principled method, named GAGA, to improve generation efficiency without sacrificing training granularity or inference fidelity of GPPGMs. Our key insight is that different data modalities obtain sufficient Gaussianity at markedly different steps during the forward process. Based on this observation, we analytically identify a characteristic step at which molecular data attains sufficient Gaussianity, after which the trajectory can be replaced by a closed-form Gaussian approximation. Unlike existing accelerators that coarsen or reformulate trajectories, our approach preserves full-resolution learning dynamics while avoiding redundant transport through truncated distributional states. Experiments on 3D molecular generation benchmarks demonstrate that our GAGA achieves substantial improvement on both generation quality and computational efficiency.

Speaker: Jingxiang Qu

Location: New Computer Science 220
Virtual Job Fair for New Stony Brook Graduates & Experienced Alumni Using a platform called Career Fair Plus, participants will be able to schedule 10-minute video meetings with participating employers of interest to them. Recent graduates and alumni can register and learn more about how the fair will be run by registering on Handshake.
Zoom Like a Pro! Unlock Whiteboard, Polls, AI Companion, and more to supercharge student participation. This hands-on workshop explores innovative ways to use Zoom's built-in tools to enhance active learning activities in your classes. Learn how to utilize the Whiteboard feature to make collaborative work more engaging, use Polling and Quizzes for instant feedback, AI Companion for summary, and Breakout Sessions for group activities. Register here: https://stonybrook.zoom.us/meeting/register/tJckf--rpj4pGdRV0ItgTW8Lk7gn_RuykByO#/registration
The Collective Surgical Consciousness: Artificial Intelligence & the Future of Surgery Guest speaker Doctor Ozanan Meireles, the Director of the Surgical AI and Innovation Lab at Massachusetts General Hospital and a faculty member at Harvard Medical School, presents The Collective Surgical Consciousness: Artificial Intelligence & the Future of Surgery. Objectives: * Become familiar with the subfields of AI used in surgery * Understand the importance of a potential paradigm shift in surgical practice, training, and continue medical development * The importance of data acquisition, sharing and ownership, and development of machine learning algorithms
Hieu Le presents Incorporating Physical Illumination Constraints into Deep Learning Shadow Detection and Removal (PhD Proposal)

Shadows provide useful cues to analyze the scene but also hamper many computer vision algorithms such as image segmentation, object detection or tracking. For those reasons, shadow detection and shadow removal have been well studied topics in computer vision. Early approaches for shadow detection and removal focus on physical illumination models of shadows. These methods can express, identify, and remove shadows in a physically plausible manner. However, these models are often hard to optimize and slow in inference due to reliance on hand-designed image features. On the other hand, recent deep-learning approaches have achieved breakthroughs in performances for both shadow detection and removal. They learn to extract useful features automatically through training while being extremely efficient in computation. However, these models are data-dependent, opaque and ignore the physical aspects of shadows.

We propose to incorporate physical illumination constraints into deep-learning frameworks. Thus the mapping learned by the deep-network closely follows the physics of shadows, enabling the network to systematically and realistically modify shadows in images. For shadow detection, we present a novel GAN framework in which the generator can generate realistic images with attenuated shadows that can be used to train a shadow detector. For shadow removal, we propose a method that uses deep-networks to estimate the unknown parameters for a shadow image formation model that removes shadows. The system outputs shadow-free images in high-quality with no image artifacts and achieves state-of-the-art shadow removal performance. Lastly, we propose a system trained without the need for any shadow-free images in which physical constraints play pivotal roles that enable training the networks.

For Zoom information, please email events@cs.stonybrook.edu.

Learn how SBU staff are using AI.

Over the past year, we've explored the AI tools and services available at Stony Brook. Now it's time to hear from colleagues who are putting these tools to work in their everyday roles. Join Tamara Gregorian, Herb Schramm, and Allie Seal moderated by David Ecker as they share how they use AI in their position, the tasks it helps them accomplish and the lessons they've learned along the way. This session is an opportunity to see practical examples, ask questions, and gather ideas that you can apply in your own work.

Register here.

Educational objectives:
  1. Describe the data modalities available in All of Us (EHR, genomics, wearables) and explainhow OMOP CDM standardization enables reproducible cohort definitions across CDRversions.
  2. Evaluate the role of AI-assisted coding tools in accelerating the research-to-manuscriptpipeline while maintaining investigator oversight and scientific rigor.
  3. Apply a secure two-environment workflow to distinguish between exportable code artifactsand environment-bound data outputs when working within controlled-access researchplatforms.


Speaker: Hants Williams, Ph.D., R.N., Applied Health Informatics, Stony Brook University

Location: MART Building, Room: 7M-0602 (7th Floor)

Zoom: https://stonybrook.zoom.us/j/95617197636?pwd=KytzZ2pVRG9SZGpKZUtpNXJISjNjZz09
Meeting ID: 95617197636
Passcode: 924293
Abstract: Molecular learning has become an emerging field of AI, driving breakthroughs in drug discovery, protein design, and materials design. For high-stakes scientific tasks, however, predictive accuracy alone is not sufficient: models must also be interpretable and trustworthy. Our work aims to study molecular learning under a unified explainability perspective across two major model families: Graph Neural Networks (GNNs) and Large Language Models (LLMs).

GNNs are natural choices for molecular graphs and achieve strong performance on many molecular tasks. To enhance explainability, many GNN explanation methods have been proposed and work well for 2D GNNs. However, 3D GNNs introduce two key challenges: producing chemically meaningful substructures and reducing fidelity loss caused by dense geometric graphs. To address these challenges, I present two methods. 3DGraphX decomposes dense 3D graphs into chemically meaningful 3D motifs, enabling compact explanations that align with chemical intuition. EDMA introduces an energy-based discrete mask approximation approach to reduce the discrepancy between the soft mask optimized during training and the hard mask used for explanation, improving explanation fidelity.

LLMs present different characteristics and challenges compared with GNNs. LLMs can provide a certain level of explanation through step-by-step reasoning, and their natural-language outputs are easy for humans to understand and interpret. However, because LLMs are trained for general-purpose tasks, their performance on scientific tasks often lags behind specialized GNNs. To improve performance, existing methods guide LLMs by providing suggestions through brief feedback, retrieval-augmented generation (RAG), or planner agents. However, these approaches face several limitations, such as vague guidance, introduced bias problems, and high computational cost. To fill the gap, I propose RL-Guider, a lightweight reinforcement-learning agent that converts evaluation feedback into input-specific guidance for molecular optimization. RL-Guider improves over time by accumulating historical experience and transfers efficiently across different LLMs while preserving interpretability.

Together, these efforts aim to provide explanations that are scientifically meaningful and faithful, while also preserving or improving performance on molecular tasks to better meet real scientific needs.

Speaker: Xufeng Liu

Location: New Computer Science-1-Room 115