TITLE: Towards a Theory of Encode/Decoder Architectures by Andrej Risteski of CMU

ABSTRACT: A common choice of architecture in representation learning (i.e., learning a good embedding of the data) is an encoder/decoder architecture, which tries to map a part of the input into a good latent representation (via an encoder), and predict the remaining part of the input (via a decoder). Two common examples are universal machine translation: where one tries to learn to translate between any pair of a set of languages via a common latent language, given paired up corpora for only a part of the pairs; and contextual encoders -- where one tries to predict a part of the image, given the rest of the image.
 
We will give a framework for analyzing the sample complexity of such architectures -- i.e., how many pairs of languages do we need to have paired up corpora for? How many image prediction tasks do we have to solve to get a good representation?

Stony Brook University Libraries invites students, faculty, & staff to join a conversation about how AI is transforming the private sector workforce. As AI tools move from experimentation to everyday business use, companies are rethinking roles, skill sets, leadership, and long-term strategy. This discussion-based event will focus on the fast-paced changes and directions at tech companies and their possible impact. This event will be particularly relevant for students preparing for an AI influenced job market and how to position themselves for opportunities in a rapidly evolving professional landscape.

The discussion will be led by Tariq Khan, Senior Director of Private Cloud Solutions at Hewlett Packard Enterprise. Tariq is a technology leader and architect with experience across private cloud, hybrid cloud, and data center platforms. He is responsible for shaping the technology architecture and strategic direction of HPE's Private Cloud offerings across on premises and cloud integrated environments.

Light refreshments will be served.


Location: Melville Library, NRR, Learning Lab

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

Maria Zawadowicz, EBNN--ML for Atmospheric Aerosol Research

Mohammad Atif, CDS--An Extensible Digital Twin Framework

Guang Zhao, CDS--Pareto Prompt Optimization

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

Meeting ID: 161 528 9117
Passcode: 991382

This symposium will highlight how artificial intelligence (AI) can assist in dementia detection, research and clinical care. For example, the use of robotics to assist with dementia care therapy is truly inspirational and cutting-edge for clinicians, trainees and the community at large, including assisted living facilities. The symposium will also focus on the role of AI in early detection of dementia and in identifying characteristics associated with future cognitive decline.

Learn more and register at https://cme.stonybrookmedicine.edu/continuing-medical-education/conferences/233/alzheimers-symposium-ai-the-future-of-dementia-care-2024/11/15/2024


Abstract: In high-dimensional data spaces, vast empty regions often exist where no known data points are present. These empty spaces are not merely gaps but hold untapped potential for discovering novel configurations, optimizing parameters, and improving decision-making processes. However, traditional exploration techniques struggle to identify and leverage these regions due to the curse of dimensionality. To address this, we introduce the Empty Space Search Algorithm (ESA), a scalable, physics-inspired method that systematically identifies and explores these uncharted voids. ESA operates by modeling the data space as a dynamic system, using a repulsion-attraction mechanism to locate optimal empty space configurations (ESCs) without requiring exhaustive search. Building upon ESA, we present GapMiner, a visual analytics system that integrates human-in-the-loop AI to iteratively refine and validate ESCs. GapMiner combines parallel coordinate visualization, interactive optimization, and deep learning-based predictive modeling to enhance the efficiency of empty space exploration. This methodology has broad applications, including accelerating convergence in evolutionary algorithms through a more diverse initial population, optimizing adversarial learning strategies, and discovering novel parameter configurations in reinforcement learning. Our approach demonstrates that empty space is not just an absence of data but a frontier for new possibilities in high-dimensional problem-solving.
Bio: Xinyu Zhang received his B.E. in Computer Science from Shandong University, Taishan College, in 2019. He is currently a final-year Ph.D. candidate in the Department of Computer Science at Stony Brook University, advised by Prof. Klaus Mueller. His research focuses on multivariate data analysis, scientific visualization, and reinforcement learning. He has published multiple papers in top-tier journals and conferences, including IEEE TVCG and NeurIPS.
*this seminar will be held in person (food provided on a first come, first serve basis), and online (zoom link below)!
Topic: IACS Student Seminar Speaker: Xinyu Zhang
Time: Feb 26, 2025 12:00 PM Eastern Time (US and Canada)
Join Zoom Meeting
https://stonybrook.zoom.us/j/91848218975?pwd=lfITFa61GaXZ2Wsa1B1OnbLQMmXvOE.1

Meeting ID: 918 4821 8975
Passcode: 027337
IACS and the Dept of Ecology and Evolution invite you to a PRODiG+ Fellowship Seminar.

Computational Approaches to Understanding and Forecasting Biodiversity Responses to Global Change

Summary: Advancing biodiversity forecasting requires developing computational approaches that better represent ecological complexity. In this talk, I will discuss how my research integrates field observations, predictive modeling, machine learning, and spatiotemporally explicit environmental data to develop more mechanistic and reliable forecasting tools.

Speaker: Dr. Anna Thonis, a postdoctoral researcher in NYU's Winchell Lab and Founder and Co-Chair of the IUCN SSC Anoline Lizard Specialist Group, studies how anthropogenic change reshapes the distributions of reptiles. Combining field and quantitative modeling methods, her work focuses on the ecology and conservation of Puerto Rican and urban Anolis lizards. Her website can be accessed here.

Location: IACS Seminar Room, and via Zoom.

Zoom: https://stonybrook.zoom.us/j/97023584426?pwd=HrnrYeYJfVUhaS8iOKjWF3Tbh8HYS1.1&jst=2
ID: 97023584426
Passcode: 241762
Join us at the Center for Excellence in Learning and Teaching (CELT) for an interactive Zoom workshop on Generative AI designed for faculty and staff interested in enhancing teaching and assessment practices, increasing student engagement, and navigating the rapidly evolving landscape of AI tools. Participants will be introduced to common AI tools, explore potential instructional uses, and discuss key considerations such as academic integrity, transparency, and equity.
Register now: https://stonybrook.zoom.us/meeting/register/6js1eP64T1ys8tyU57EJ7Q#/registration
West Campus - SAC- Student Activities Center - Ballrooms A & B 100 Nicolls Road Stony Brook NY 11794 Job Fair.jpg The Career Center invites Alumni Employers and Job Seekers to the IT/Computer Science Job and Internship Fair this spring. Job Seekers: A job fair is an opportunity for you to present yourself professionally in person to a potential employer, while showcasing your communication skills. Get more information Alumni Employers: Held in both the fall and spring semesters, this event is ideal for employers looking to fill internship, co-op, part-time and full-time opportunities in the field of information technology (i.e. Software Engineering, Network Administration, Web Development, etc.). Register here to recruit top SBU talent.

You are cordially invited to attend the biweekly Brookhaven AI Mixer (BAM). BAM includes one short talk 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.

#1 How to train your Scientific Chatbot by Alexandr Prozorov, Post-Doctoral Research Associate


Abstract: RHIC is closing its 25-year run with ~1 EB of data and decades of hard-won know-how that risk drifting into obscurity. The RHIC Data & Analysis Preservation Plan (DAPP) pilots an AI assistant that lets physicists talk to RHIC in natural language--searching internal notes, code, workflows, and docs, and pointing to runnable, containerized analyses. Built on Retrieval-Augmented Generation(RAG) with a Model Context Protocol orchestration layer, the system indexes heterogeneous, experiment-specific content and enforces role-aware access
for public vs. collaboration-restricted materials. Takeaway: domain-adapted AI can turn a legacy exabyte into reproducible answers, training assets, and new discovery paths.

Biography: Alexandr Prozorov is a postdoc from Czech Technical University in Prague working in STAR experiment. Fascinated by AI

#2 Quantum AI: Atoms, Cavities and Learning by Raman Kumar, Post-Doctoral Research Associate, Instrumentation Department

Abstract: The Instrumentation Department (IO) in the Discovery Technologies directorate at BNL is engaged in exploring various aspects of quantum systems research. One of the main goals of our group's effort is in developing neutral atom-cavity array platforms for remote entanglement generation and distributed quantum processing. This platform promises to herald truly scalable quantum computing systems and open new paradigms for networking and sensing. In this talk, I will explain our group's research and the role AI is playing in unlocking new insights with two examples. The first application of AI is in fabrication process prediction of micro-cavity structures. The second application revolves around role of AI in quantum error detection and correction in modern quantum computing systems.

Biography: Dr. Raman Kumar is a postdoctoral research associate in the IO department at BNL working with Dr./Prof. Sebastian Will (Columbia U.). Kumar obtained his Ph.D. degree in Electrical and Computer Engineering from the University of Illinois Urbana-Champaign. Prior to joining BNL in Nov 2024, Kumar worked as a postdoc at the City College in New York working on topological photonic quantum sensing using NV centers in diamond. Kumar and Will combined have an extremely wide moat and expertise in a variety of different areas which include Ultra cold atoms and molecules, quantum optics, quantum condensed matter, nanofabrication, semiconductor devices and advanced electromagnetics. Their areas of research interest include scalable quantum computing, communications and sensing, all enabled by AI.

Location: CDS, Bldg. 725, Training Room

Join ZoomGov Meeting https://bnl.zoomgov.com/j/1607892208?pwd=MSjxN5btSeToZsQMwEQzCCbBo5h58V.1

Meeting ID: 160 789 2208
Passcode: 753871

Abstract: Generative models have transformed natural image synthesis, driven by billion-scale datasets of image-caption pairs. Specialized domains, such as digital histopathology and satellite imagery, differ in two ways: their images reach gigapixel resolution, far beyond any feasible training resolution, and they lack paired captions, since captioning the patches of a single whole-slide image (WSI) takes about 40 hours of pathologist time. Overcoming these challenges would enable generative models that create teaching cases of rare diseases, simulate tumor progression, and serve as a foundation for digital twins.

In this thesis, we build generative foundation models for these domains, scaling from small patches to gigapixel images without patch-level annotations. We begin with PathLDM, which conditions histopathology patch generation on
slide-level pathology reports, enabling the first text-to-image generation in histopathology. Since reports do not describe individual patches, we propose LRDM, which uses embeddings from pretrained self-supervised learning (SSL) encoders as patch-level conditioning for both histopathology and satellite images. ZoomLDM extends SSL conditioning across eight magnifications with a single model, capturing structure from individual cells to tissue architecture. To scale across cancer types, we present PixCell, the first generative foundation model for histopathology, trained on 30.8 million patches from 69,184 WSIs across 28 organ types. Synthetic images from PixCell can stand in for real data in SSL training, enable privacy-preserving data sharing, and improve downstream tile-level classifiers. Extending this to gigapixel scale, we introduce BigCell, which generates coherent WSIs of up to 32768x32768 pixels by guiding a 2048x2048 flow-matching transformer with a grid of foundation model embeddings, and speeds up generation by over 3x with an importance-based schedule. BigCell enables text-to-image synthesis at 8192x8192 resolution, with synthetic samples improving slide-level few-shot classification by up to 18%. Beyond pathology, our SSL-conditioned models serve as data generators for self-supervised learning on natural images. Finally, to make gigapixel synthesis practical, we plan to reduce BigCell's generation time from about 5 hours to under 20 minutes per 32768x32768 image through few-step distillation and efficient attention, and to extend text-to-image synthesis from 8192x8192 regions to entire slides with a pretrained language model.

Speaker: Srikar Yellapragada

Location: NCS 220