Events

Speaker: 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 reveals elegant nonconvex geometry in various benchmark problems. In this talk, we introduce an Extended Convex Lifting (ECL) framework, which reveals hidden convexity in classical optimalContinue reading "Optimization for ML and AI Seminar: Extended Convex Lifting for Policy Optimization in Control"

Speaker: 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 3D IC architecture enables substantial improvements in energy efficiency and latency by optimizing inter chip data transfer. At the core of this transformation lies the automationContinue reading "TILOS-MICS Seminar: AI-Driven Design Automation for Multi-Chip Integration in AI Chips"

Speaker: 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 address their expressivity, we consider the case that the mappings are conditioned on a context represented by a probability distribution of tokens. That is, transformers becomeContinue reading "TILOS Seminar: Kinetic Theory Perspective of Foundation Models for Physics"

Speaker: 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 series of frontier reasoning LLMs developed out of an academic lab, from data curation and pre-training to post-training and alignment. These models surpass leading LLMs fromContinue reading "TILOS Seminar: Neuromorphic LLMs"