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. 

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.

At our Oct 7 Mixer, BNL's newly minted interim director, John Hill will be present to give opening remarks and kick us off on a new year of impactful scientific AI collaborations.

Abstract: Weather extremes and strong seasonal-to- subseasonal variability pose growing challenges to urban populations, infrastructure, and energy systems. Yet, most cities remain data deserts: routine weather observations are sparse, with stations concentrated at airports rather than within the urban core. This lack of coverage limits our ability to monitor and predict fine-scale urban weather patterns precisely where they matter most. We present a new AI-driven framework for optimal sensor placement and urban weather monitoring. Unlike traditional approaches, our method leverages physics- based simulations together with Bayesian experimental design principles, but does so using a computationally efficient variational inference strategy that makes large-scale optimization tractable. This allows us to guide sensor networks in a way that minimizes information loss while capturing spatiotemporal variability at city scales. Applied to Phoenix, Arizona, our framework outperforms random sensor placement strategies, especially when only a limited number of sensors can be deployed. Importantly, the same AI models that guide sensor placement also function as a real-time nowcasting tool, providing urban weather information over the entire domain, beyond sensor locations. Together, these capabilities offer a scalable pathway to reduce urban data deserts, enhance monitoring of weather extremes, and improve resilience planning for energy, transportation, and public health systems.

Biography: Dr. Katia Lamer is an atmospheric scientist and the Director of the Center for Multiscale Applied Sensing at Brookhaven National Laboratory. Originally from Canada, she earned her B.S. and M.S. in Atmospheric and Oceanic Sciences from McGill University and a Ph.D. in Meteorology from Penn State University. Her research focuses on atmospheric boundary layer processes and remote sensing technologies, with a strong emphasis on data science. At Brookhaven, she is known for her work with the CMAS mobile observatories and its facility that connect fundamental atmospheric science to real-world applications, improving weather prediction, environmental monitoring, and urban climate resilience. Her work has been featured in public outlets such as New Scientist and Wired. Dr. Lamer also serves as an invited member of the World Meteorological Organization's Data Assimilation and Observing Systems Working Group, and the American Meteorological Society's Boundary Layer and Turbulence Committee. puting, communications and sensing, all enabled by AI.

Location: CDS, Bldg. 725, Training Room

Join ZoomGov Meeting: https://bnl.zoomgov.com/j/1604383624?pwd=ffQ5cUPNxTI7nzClKQO6cnsNbhF9Vf.1

Meeting ID: 160 438 3624 | Passcode: 558449

Topic: AI Seminar: Owen Rambow
Time: Mar 17, 2021 10:00 AM Eastern Time (US and Canada)
Join Zoom Meeting

https://stonybrook.zoom.us/j/93614644178?pwd=MzJtVDJYYmU5T1dtMzJiUFMxb0x4dz09
Meeting ID: 936 1464 4178.    Passcode: 965936






Natural Language Understanding and Semantic Parsing

(Partly joint work with former colleagues at Elemental Cognition)

Semantic parsing refers to the task of determining the propositional content of language: who did what to whom.  It is part of the larger task of natural language understanding (NLU).  I will start out by discussing what full NLU means, and argue that we are still far away, as a field, from solving full NLU, or even from knowing how to evaluate it.

In the second part of the talk, I will situate semantic parsing in the context of several other NLU subtasks.  Typically, the target representation of semantic parsing uses an ontology (such as PropBank or FrameNet).  Semantic parsing includes the subtasks of word sense disambiguation, argument detection, and argument role labeling.  I will discuss choices among possible target ontologies.  I will justify why we created a new ontology, Hector, based on FrameNet and the lexical resource NOAD, and explain some of its characteristics.

In the third part of the talk, I will present experiments we performed using transformer models.  We obtain best results using a two-phase model, in which we first choose the frame, and then, given the frame, choose the arguments.  We encode the problem for both tasks using indices in the sentence.  While we develop the parser for our new ontology Hector, this approach also beats the state of the art for FrameNet and PropBank parsing.Biography:  I am a professor in the Department of Linguistics at Stony Brook University with a joint appointment in IACS.

Until recently, I was a research scientist at Elemental Cognition. Elemental Cognition is working on deep natural language understanding.

I got my PhD with Aravind Joshi at the University of Pennsylvania in 1994. I have worked at CoGenTex, and at AT&T Labs -- Research, and for many years I was a research scientist at Columbia University in the Center for Computational Learning Systems.


Abstract: Pretraining vision encoders with self-supervision (SSL) leads to stronger representations that excel across diverse downstream tasks. One of the key factors enabling self-supervision is extracting multiple views of the same scene to formulate either: 1) View-invariant pretraining (DINO, SimCLR, iBOT), where the objective is predicting the same representation for different views of the scene; or 2) Cross-view pretraining (cross-view Masked Autoencoders), where the objective is predicting missing parts of one view using other views. For extracting multiple views, view-invariant methods rely on a combination of handcrafted augmentations (random cropping, color jittering, gaussian blur, etc.) of the same image, whereas cross-view pretraining methods rely on image cropping or video frames. In this work, we present methods to effectively incorporate synthetic views from diffusion models into SSL training.
For view-invariant pretraining, we introduce Gen-SIS, a method that leverages the ability of diffusion models to generate interpolated images through interpolation in conditioning space. We introduce a disentanglement pretext task: disentangling two source images from an interpolated synthetic image. This disentanglement task, in addition to vanilla single-source generative augmentation for view extraction, improves visual pretraining of various view-invariant methods (DINO, SimCLR, iBOT).
For cross-view pretraining, we introduce CDG-MAE, a novel cross-view masked autoencoder (MAE) based method that uses diverse synthetic views generated from static images via an image-conditioned diffusion model to learn dense correspondences. We present a quantitative method to evaluate the local and global consistency of the generated views to choose the right diffusion model for cross-view pretraining. These generated views exhibit substantial changes in pose and perspective, providing a rich training signal that overcomes the limitations of video (expensive) and crop-based (less variation) methods. CDG-MAE substantially narrows the gap to video-based MAE methods on video label propagation tasks while maintaining the data advantages of image-only MAEs.

Speaker: Varun Belagali

Location: NCS 120
Zoom: https://stonybrook.zoom.us/j/93647452432?pwd=hZaX7LXCAD8KPHWYE1Afw2sDI3owpv.1

The Vedanta Forum is devoted to one of humanity's oldest and most profound pursuits -- thinking. Thinking about who we truly are: the one that remains constant through childhood and old age, through waking, dream, and deep sleep. Thinking about the source and cause of creation, and its relationship to what inheres in us.

Across history, such thinking, both meditative and scientific, has been aimed at these questions. The ancient Upanishads proclaimed, Tat Tvam Asi -- Thou Art That -- revealing the non-dual identity of the individual and the ultimate reality. Centuries later, modern scientists such as Schrödinger and Bohr echoed similar intuitions about the unity of existence.

Over time, many philosophical approaches, traditions, and interpretive schools have arisen from such inquiry, each offering unique perspectives. The Forum will:

  • Focus on universal approaches and traditions and examine their teachings,

  • Foster comparative studies, and

  • Explore the practical benefits to society from such thinking,

through scholarly studies, dialogue, and debate also promoting accessibility to all qualified seekers. Additionally, the Forum will explore how these reflections can enrich life, education, and even technology.

Location: NCS 120 (New Computer Science), Engineering Dr, Stony Brook, NY 11794.

The program is available at: https://www.vedantaforum.org/events/program

Abstract: Autonomous systems, whether on Earth or in space, rely on 3D perception to understand and interact with the world around them. Yet traditional techniques for 3D understanding often depend on human designed features, fixed sensors, and conventional imaging modalities. This constrained approach can limit every stage of perception, from sensing to interpretation to decision making.
In this talk, we'll explore an alternative paradigm for imaging: physically based neural representations for 3D scenes and 3D sensing systems. We will discuss how recent advances in large scale learned representations can be used to jointly optimize both 3D scene models and the design of sensing systems for 3D capture, with the goal of enabling task specific perception systems.
Unlike modern AI models trained on internet scale datasets, these specialized 3D representations typically operate in data sparse regimes and therefore require a different kind of prior. We'll examine how grounding these learned representations in the physics of light transport can improve our understanding of scene structure, and inform imaging system design even with limited data. By connecting physical insights with learned representations, we'll highlight new possibilities for robust, efficient, and adaptive perception in challenging environments.

Speaker: Nikhil Behari is a graduate student in the Camera Culture group at the MIT Media Lab, advised by Professor Ramesh Raskar. His research interests include computational imaging, 3D scene understanding, and multi-agent decision-making under uncertainty, with a focus on automating imaging system design for 3D perception in human and planetary health. His research is supported by the NASA Space Technology Graduate Research Fellowship. He received his bachelor's in Computer Science and Statistics from Harvard University in 2022.

Abstract: Large Language Models (LLMs) have revolutionized how people interact with knowledge, offering unprecedented opportunities to accelerate the pace of scientific discovery. In this talk, I will discuss my research on the synergy between LLMs and scientific knowledge--specifically how these models extract, induce, and verify knowledge to automate the research lifecycle. First, I will cover our work on improving knowledge extraction from vast scientific literature, focusing on enabling models to comprehend long documents in a cost-efficient and comprehensive manner. I will describe a novel paradigm for representing document-level structured information as question-answer pairs and how we address the challenges of long-context understanding by leveraging global context through retrieval-augmented modeling. Next, I present our pioneering work on using LLMs for new scientific hypothesis generation. We introduce a framework employing reinforcement learning with fine-grained reward modeling and adaptive controllers.
This approach balances novelty, feasibility, and effectiveness to generate inspiring and actionable research hypotheses. Finally, I will discuss work on the first LLM Scientist for machine learning research. I will demonstrate how LLMs can move beyond hypothesis generation to participate in the execution and validation of scientific hypotheses, ensuring that the discovered knowledge is not only innovative but also grounded and verified.

Bio: Xinya Du is a tenure-track assistant professor at UT Dallas Computer Science Department. He earned a Ph.D. degree from Cornell University and was a Postdoctoral Research Associate at the University of Illinois (UIUC). He has also worked at Microsoft Research, Google Research, and Allen Institute AI. His research is on large language models, deep learning, and their applications in science.His work has been published in leading NLP and ML conferences (ACL, ICLR, NeurIPS). His research has received multiple recognitions, including a Best Paper Award at AAAI AI for Research and a Best Poster Award at ICML AI for Science workshop. His work was included in the list of Most Influential ACL Papers and has been covered by major media like New Scientist. He was named a Spotlight Rising Star in Data Science by the University of Chicago and is the recipient of several prestigious awards, including the Amazon Research Award, Cisco Research Award, Open Philanthropy Award, and the NSF CAREER Award.

Location: NCS 120




Time: 04/28 Wed 3pm-4pm

Remote Access
Join Zoom Meeting https://stonybrook.zoom.us/j/95617197636?pwd=KytzZ2pVRG9SZGpKZUtpNXJISjNjZz09 
Meeting ID: 956 1719 7636 Passcode: 924293

Title: Brain imaging genetics for Alzheimer's disease: integrated analysis and machine learning

Li Shen, Ph.D.
Professor of Informatics
Department of Biostatistics, Epidemiology and Informatics 
Perelman School of Medicine
University of Pennsylvania

Bio: Li Shen, Ph.D., is a Professor of Informatics in the Department of Biostatistics, Epidemiology and Informatics at the Perelman School of Medicine in the University of Pennsylvania. He is an elected fellow of the American Institute for Medical and Biological Engineering (AIMBE). He obtained his Ph.D. degree in Computer Science from Dartmouth College. The central theme of his lab is focused on developing computational and informatics methods for integrative analysis of multimodal imaging data, high throughput omics data, cognitive and other biomarker data, electronic health record (EHR) data, and rich biological knowledge such as pathways and networks, with applications to complex disorders. His research interests include medical image computing, biomedical informatics, machine learning, network science, imaging genomics, Alzheimer's disease, and big data science in biomedicine. He has authored over 280 peer-reviewed articles (h-index 57) in these fields. Dr. Shen's work has been continuously supported by the NIH and NSF, and he is presently the PI of multiple NIH and NSF grants on developing computational methods for various biomedical applications including brain imaging genomics, genetics of Alzheimer's disease, genetics of human connectome, mining drug effects from the EHR data, and big data mining in brain science. He is co-leading the NIA Alzheimer's Disease Sequencing Project AI4AD Consortium and oversees the imaging genomics aspect of this landmark project. Dr. Shen served as the Executive Director of the Medical Image Computing and Computer Assisted Intervention (MICCAI) Society Board of Directors during 2016-2019. He has chaired and co-chaired various professional meetings in medical image computing and bioinformatics. He is an Associate Editor of BioData Mining and Frontiers in Radiology (Section of AI in Radiology), and serves on the Editorial Board of Medical Image Analysis and Brain Imaging and Behavior.

Abstract: Brain imaging genetics is an emerging data science field, where integrated analysis of brain imaging and genetics data, often combined with other biomarker, clinical and environmental data, is performed to gain new insights into the genetic, molecular and phenotypic characteristics of the brain as well as their impact on normal and disordered brain function and behavior. Many methodological advances in brain imaging genetics are attributed to large-scale landmark biobank projects such as the Alzheimer's Disease Sequencing Project, the Alzheimer's Disease Neuroimaging Initiative, and the UK Biobank. Using the study of Alzheimer's disease as an example, we will discuss fundamental concepts, state-of-the-art statistical and machine learning methods, and innovative applications in this rapidly evolving field. We show that the wide availability of brain imaging genetics data from various large-scale biobanks, coupled with advances in biomedical statistics, informatics and computing, provides enormous opportunities to contribute significantly to biomedical discoveries in brain science and to impact the development of new diagnostic, therapeutic and preventative approaches for complex brain disorders such as Alzheimer's disease.

More details:
https://bmi.stonybrookmedicine.edu/sites/default/files/shen_li_04_28_flyer.pdf