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 addressContinue 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 seriesContinue reading "TILOS Seminar: Neuromorphic LLMs"
Speaker: 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"