9 events found.
Seminar Series
Events
-
-
-
TILOS Seminar: Incentivizing Emergent Behaviors for LLMs via Reinforcement Learning
Zoom: https://bit.ly/TILOS-Seminars
-
-
Optimization for ML and AI Seminar: Randomized linear algebra with subspace injections
Halicioglu Data Science Institute Room 123 3234 Matthews Ln, La Jolla, CA, United StatesZoom: https://bit.ly/Opt-AI-ML
-
TILOS Seminar: Safety, Representations, and Generative Learning in Dynamical Systems
Halicioglu Data Science Institute Room 123 3234 Matthews Ln, La Jolla, CA, United StatesZoom: https://bit.ly/TILOS-Seminars
-
-
Optimization for ML and AI Seminar: Extended Convex Lifting for Policy Optimization in Control
Halicioglu Data Science Institute Room 123 3234 Matthews Ln, La Jolla, CA, United StatesSpeaker: Yang Zheng, UC San Diego Abstract: Direct policy search has achieved great empirical success in reinforcement learning. Many recent studies have revisited its theoretical foundation for continuous control, which revealsContinue reading "Optimization for ML and AI Seminar: Extended Convex Lifting for Policy Optimization in Control"
-
TILOS-MICS Seminar: AI-Driven Design Automation for Multi-Chip Integration in AI Chips
Halicioglu Data Science Institute Room 123 3234 Matthews Ln, La Jolla, CA, United StatesSpeaker: Sung-Kyu Lim, University of Southern California Abstract: Multi-chip integration has become a standard approach in AI training and is rapidly gaining traction in edge learning applications. Leveraging 2.5D and 3DContinue reading "TILOS-MICS Seminar: AI-Driven Design Automation for Multi-Chip Integration in AI Chips"
-
TILOS Seminar: Kinetic Theory Perspective of Foundation Models for Physics
Halicioglu Data Science Institute Room 123 3234 Matthews Ln, La Jolla, CA, United StatesSpeaker: Maarten de Hoop, Rice University Abstract: We present a kinetic theory perspective of foundation models for physics. We begin with providing a mathematical framework for analyzing transformers. To uniformly addressContinue reading "TILOS Seminar: Kinetic Theory Perspective of Foundation Models for Physics"
-
TILOS Seminar: Neuromorphic LLMs
Halicioglu Data Science Institute Room 123 3234 Matthews Ln, La Jolla, CA, United StatesSpeaker: Jason Eshraghian, UC Santa Cruz Abstract: This talk will show you what neuromorphic computing can do when an academic lab accidentally pulls $2-million of GPU-hours. We will showcase a seriesContinue reading "TILOS Seminar: Neuromorphic LLMs"
-
Optimization for ML and AI Seminar: (De)regularized Wasserstein Gradient Flows via Reproducing Kernels
Halicioglu Data Science Institute Room 123 3234 Matthews Ln, La Jolla, CA, United StatesSpeaker: Bharath Sriperumbudur, Pennsylvania State University Abstract: Wasserstein gradient flows have become a popular tool in machine learning with applications in sampling, variational inference, generative modeling, and reinforcement learning, among others.Continue reading "Optimization for ML and AI Seminar: (De)regularized Wasserstein Gradient Flows via Reproducing Kernels"