Recorded Talks

  • IFML Seminar: 9/27/24 - Computationally Efficient Reinforcement Learning with Linear Bellman Completeness

    Noah Golowich , PhD Student, MIT

  • IFML Seminar: 9/13/24 - On the Computational Complexity of Private High-dimensional Model Selection

    Saptarshi Roy, Postdoc Research Fellow, The University of Texas at Austin

  • IFML Seminar: 9/6/24 - Perceiving Humans in 4D

    Georogios Pavlakos, Assistant Professor, UT Austin

  • IFML Seminar: 8/23/24 - Clued-in to Clueless: Navigating Distribution Shifts with Varying Levels of Target Distribution Information

    Olawale Salaudeen, Postdoctoral Associate, MIT CSAIL

  • IFML Seminar: Generating a Video: Reflecting on a Two-Year Odyssey

    Atlas Wang, Associate Professor, UT Austin

  • AIHealthTalk : 4/10/24 - Towards Digital Twins for Cardiovascular Health: From Clinical To Remote

    Bobak Mortazavi, Associate Professor, Texas A&M University

  • IFML Seminar: 4/5/24 - Robustness in the Era of LLMs: Jailbreaking Attacks and Defenses

    Hamed Hassani, Associate Professor, The University of Pennsylvania

  • AIHealthTalk : 4/3/24 - The Generalist Medical AI Will See You Now

    Pranav Rajpurkar, Assistant Professor, Harvard University

  • AIHealthTalk : 3/27/24 - Shaping the Creation and Adoption of Large Language Models in Healthcare

    Nigam Shah, Professor, Stanford University

  • AIHealthTalk: 3/20/24 - How LLMs Might Help Scale World Class Healthcare to Everyone

    Vivek Natarajan, Research Scientist, Google Health

  • IFML Seminar: 3/8/2024 - An Lyapunov Analysis of the Lion Optimizer

  • IFML Seminar: 2/23/2024 - Recent Advances in Parallel Stochastic Convex Optimization

  • IFML Seminar: 3/1/2024 - On Solving Inverse Problems Using Latent Diffusion-based Generative Models

    Sanjay Shakkottai, Professor Cockrell Family Chair in Engineering # 1, UT Austin

  • IFML SEMINAR: 2/16/24 - Long Context Foundational Models

    Srinadh Bhojanapalli, Research Scientist at Google Research

  • IFML SEMINAR: 2/2/24 - Gromov-Wasserstein Alignment: Statistical and Computational Advancements via Duality

  • IFML SEMINAR: Jan 26, 2024 - Meta Optimization

    Elad Hazan, Professor, Princeton and Director and co-founder, Google AI Princeton

  • 2023 Machine Learning Lab Public Lecture with Scott Aaronson

    Scott Aaronson, theoretical computer scientist and David J. Bruton Jr. Centennial Professor of Computer Science, UT Austin

  • Machine Learning Lab 2022 Public Lecture with Alan Bovik

    Alan Bovik, Director, Laboratory for Image & Video Engineering, Machine Learning Lab, UT Austin

  • The Power of Adaptivity in Representation Learning: From Meta-Learning to Federated Learning

    Aryan Mokhtari, Assistant Professor, Electrical and Computer Engineering, UT Austin

  • Outracing Champion Gran Turismo Drivers with Deep Reinforcement Learning

    Dr. Peter Stone, David Bruton, Jr. Centennial Professor, Associate Chair of Computer Science, Director of Texas Robotics

  • Deployable Robots that Learn

    Xuesu Xiao, George Mason University (Fall 2022)

  • Multi-Modal Deep Learning of Electrocardiograms for Precision Cardiovascular Health

    Benjamin Glicksberg, Assistant Professor, Icahn School of Medicine at Mount Sinai

  • Clustering Mixtures with Almost Optimal Separation in Polynomial Time

    Allen Liu, graduate student in EECS at MIT.

  • IFML Public Lecture: AI for Accurate and Fair Imaging

    Alex Dimakis, IFML and MLL co-director

  • Optimal Control for Electroceutical Therapies

    Joshua Chang, M.D., Ph.D., Assistant Professor, Department of Neurology, The University of Texas at Austin

  • Function Space View of Bounded Weight Norm Networks

    Suriya Gunasekar (Microsoft Research)

  • The Planted Matching Problem: Sharp Threshold and Infinite-Order Phase Transition

    Dana Yang (Simons Institute)

  • Scalable and Reliable Inference for Probabilistic Modeling

    Ruqi Zhang (UT Austin)

  • Learning and Optimization With Adaptive Smoothed Adversaries

    Nika Haghtalab (UC Berkeley)

  • The Surprising Power of the Lenstra-Lenstra-Lovasz Algorithm for Noiseless Inference

    Ilias Zadik (MIT)

  • Yes, Generative Models are the New Sparsity

    Alex Dimakis, UT Austin

  • On the Power of Differentiable Learning

    Nathan Srebro (Toyota Technological Institute at Chicago)

  • A Data-Centric View On Robustness

    Ludwig Schmidt (University of Washington)

  • Evaluating AI-based MR image reconstruction models: lessons from the fastMRI project

    Matthew Muckley

  • Closing the Virtuous Cycle of AI for IC and IC for AI

    David Pan

  • Mapping timescales of cortical language processing

    Alex Huth

  • Bootstrapping the Error of Oja's Algorithm

    Purnamrita Sarkar

  • The Role of Explicit Regularization in Overparameterized Neural Networks

    Shiyu Liang

  • Mind the Gap: From Predictions to ML-Informed Decisions

    Maria De-Arteaga

  • Facing an Adult Problem: New Data Sources for Fair Machine Learning

    Moritz Hardt

  • Disparate Predictions: A Complicated Landscape

    Jamie Morgenstern

  • CityLearn: Demand Response using Multi-Agent Reinforcement Learning

    Zoltan Nagy

  • Data Analytics and ML for Subsurface Engineering and Geoscience

    Michael Pyrcz

  • Computational MRI w Deep Learning

    Jon Tamir

  • ApBio: Teaching Machines Biochemistry

    Andrew Ellington

  • Harnessing Machine Learning to Study the Life Cycle of Stars

    Stella Offner

  • N Body Hessians

    George Biros

  • Remote Sensing and AI Applications in Paleoanthropology

    Denné Reed

  • In Search of New Algorithms Part II: Graphical Models

    Adam Klivans

  • In Search of New Algorithms Part I: Neural Networks

    Adam Klivans