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

Deyu Lu
Mingyuan Ge
Kris Reyes


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

Meeting ID: 161 528 9117
Passcode: 991382


Reception to follow.

Abstract:
In this talk, I will present our journey of developing diverse, adaptive, uncertainty-calibrated AI planning agents that can robustly communicate and collaborate for multi-agent reasoning (on math, commonsense, coding, etc.) as well as for interpretable, controllable multimodal generation (across text, images, videos, audio, layouts, etc.). In the first part, we will discuss improving reasoning via multi-agent discussion among diverse LLMs and structured distillation of these discussion graphs (ReConcile, MAGDi), adaptively learning to balance abstraction, decomposition, refinement, and fast+slow thinking in LLM-agent reasoning (ReGAL, ADaPT, MAgICoRe, System-1.x), as well as confidence calibration in LLMs via speaker-listener pragmatic reasoning and making LLMs better teammates via multi-agent positive-negative persuasion balancing (LACIE, PBT). In the second part, we will discuss interpretable and control-lable multimodal generation via LLM-agents based planning and programming, such as layout-controllable image generation (and evaluation) via visual programming (VPGen+VPEval), consistent multi-scene video generation via LLM-guided planning (VideoDirectorGPT), interactive and composable any-to-any multimodal generation (CoDi, CoDi-2), as well as feedback-driven multi-agent interaction for adaptive environment/data generation via weakness discovery (EnvGen, DataEnvGym).
Bio:
Dr. Mohit Bansal is the John R. & Louise S. Parker Distinguished Professor and the Director of the MURGe-Lab (UNC-NLP Group) in the Computer Science department at UNC Chapel Hill. He received his PhD from UC Berkeley in 2013 and his BTech from IIT Kanpur in 2008. His research expertise is in natural language processing and multimodal machine learning, with a particular focus on multimodal generative models, grounded and embodied semantics, faithful language generation, and interpretable, efficient, and generalizable deep learning.

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. 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.

We meet every other Tuesday at noon in CDSD's Training Room (building 725, room 2-124) 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.

In addition to our speaker, we will have a number of CDS staff in attendance with expertise in AI methods and applications including image analysis, foundation models development, and inverse problem solving.

AI-Driven Physics-Informed Phase Retrieval from a Single X-ray

Abstract: X-ray phase-contrast imaging enables the visualization of weakly absorbing or low-contrast structures and plays an important role in materials, biological, and energy research. Conventional X-ray holography and phase-retrieval techniques typically require multiple intensity measurements acquired at different propagation distances to recover phase information, increasing acquisition time, radiation dose, and experimental complexity. In this work, we present an AI-driven, physics-informed approach for phase retrieval using only a single X-ray intensity measurement. The method adapted a generative neural network as an inverse reconstruction engine, with physical models of X-ray wave propagation embedded directly into the optimization process. This allows phase and absorption information to be recovered from a single hologram without relying on paired, unpaired, or simulated training datasets. By combining physical constraints with self-supervised AI reconstruction, the approach achieves stable and quantitative results across a wide range of imaging conditions. The results demonstrate how physics-informed AI can reduce experimental requirements and enable data-efficient, automated phase retrieval for next-generation X-ray imaging workflows.

Biography: Xiaogang Yang is a computational scientist in the Data Analysis & Workflow Integration group at NSLS-II, focusing on AI development for X-ray imaging, data analysis, and automated workflows. He earned his PhD from Delft University of Technology, completed his postdoctoral research at Argonne National Laboratory, and previously held a tenured position at PETRA III (DESY).

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

Please Note: Due to a funding shortfall, we are for the time being no longer able to provide pizza and sodas for these events. We will have coffee though, and all are of course welcome to bring their lunch.

Join us for the New York State Innovation Summit on October 28-29, 2024 in Syracuse, NY. This multi-day is event for NYS organizations that want to showcase and discover new and emerging technologies that support innovation and drive business growth. The event serves as an opportunity to foster collaboration; introduce industry to experts that can assist growth, strengthen our statewide innovation ecosystem and showcase promising early stage companies. Whether you're a startup, an economic developer, or an established manufacturer, the NYS Innovation Summit is for you. The 2024 New York State Innovation Summit will showcase companies and researchers at the forefront of emerging technologies and new advancements in production capabilities. This event celebrates New York State leadership in technology-led economic growth with experts in biotechnology, new materials, energy innovation, and artificial intelligence that will explore current technology convergence opportunities, ways to accelerate commercialization, and issues of manufacturing sustainability.
Title: Cyberinfrastructure for forward prediction and inversion estimation with uncertainty quantification

Seminar Speaker: Dr. Mengyang Gu, Assistant Professor, Department of Statistics and Applied Probability, University of California, Santa Barbara

Abstract: In this talk, we introduce four useful tools for forward prediction and inversion estimation. The first tool is the parallel partial Gaussian process surrogate model for emulating expensive computer simulations with massive coordinates. The tool is implemented in the RobustGaSP package available in R, MATLAB, and Python, for predicting both scalar- and vector-valued outputs with uncertainty assessment. The second tool is implemented in the RobustCalibration package, which handles Bayesian data inversion or model calibration by one or multiple types of experimental observations. A unique feature of the package is the inclusion of fast surrogate models of both scalar- and vector-valued computer simulations that bypass the expensive simulation in one line of code. The third tool is implemented in the AIUQ package, available in both R and MATLAB. In this approach, we show that differential dynamic microscopy, a scattering-based analysis tool that extracts dynamical information from microscopy videos, is equivalent to fitting the temporal auto-covariance in Fourier space, based on a latent factor model we construct. We develop a more efficient estimator and reduce the computational cost to pseudolinear order with respect to the number of observations without approximation, by utilizing the generalized Schur algorithm for the Toeplitz covariance. In the last tool, we developed a new method called the inverse Kalman filter, which enables fast matrix-vector multiplication between a covariance matrix from a dynamic linear model and any real-valued vector with a linear computational cost. These new approaches outline a wide range of applications that include emulating expensive simulation at molecular-, meso- and macro-scales, active learning with error control, nonparametric estimation of particle interaction functions, and data inversion from microscopy and velocity fields.

Join Zoom Meeting: https://bnl.zoomgov.com/j/1606285496?pwd=2yJYSG6lx8gMPiibzgAIBQtKHIjuHV.1
Meeting ID: 160 628 5496
Passcode: 472506
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: At XTX Markets, we view algorithmic trading as one of the most compelling real-world frontiers for deep learning and foundation models. Every day, our systems generate forecasts for tens of thousands of financial instruments and execute over $300B in global trading volume: fully automated, with no discretionary human intervention. This domain combines massive data scale with high noise, adversarial dynamics, and frequent regime shifts, making it both scientifically challenging and commercially impactful. For machine learning researchers, it serves as a rigorous proving ground where advances in time-series modeling, large-scale optimization, representation learning, and foundation models can translate directly into measurable real-world outcomes. This talk will provide a high-level overview of our research agenda, infrastructure, and key open challenges at the intersection of large-scale AI and quantitative finance.

Speaker: Dr. Zhangyang Atlas Wang is the Research Director at XTX Markets, one of the world's leading high-frequency trading firms. He founded and leads the firm's AI Lab in New York City, focused on developing large-scale foundation models for financial time series and market data, powered by XTX's proprietary AI infrastructure. He is currently on leave from his position as the Temple Foundation Endowed Associate Professor at The University of Texas at Austin. His academic research has received numerous awards, and he has mentored a broad network of Ph.D. students and postdoctoral researchers. Many of his alumni now hold tenure-track faculty positions (eight to date) or senior research roles in industry (nineteen and counting). For more information about his group and alumni, please visit: https://www.vita-group.space/team.

Location: NCS 120

Refreshments will be served after the seminar in the first-floor atrium.



The annual conference on Neural Information Processing Systems is a multi-track interdisciplinary annual meeting that includes invited talks, demonstrations, symposia, and oral and poster presentations of refereed papers. Along with the conference is a professional exposition focusing on machine learning in practice, a series of tutorials, and topical workshops that provide a less formal setting for the exchange of ideas.

For more information and registration, visit the official website.