Associate Professor · Department of Computer Science · UCLA
I lead the UCLA Artificial General Intelligence Lab, building the foundations of large language models, reinforcement learning and generative AI — and using them to accelerate scientific discovery.
I am an Associate Professor of Computer Science at UCLA. I am leading the UCLA Artificial General Intelligence Lab. I received my Ph.D. degree in Computer Science from the University of Illinois at Urbana-Champaign in 2014. My research is in artificial intelligence and machine learning, with a focus on nonconvex optimization, deep learning, reinforcement learning, Large Language Models (LLMs), and deep generative models (e.g., diffusion models). Recently, I have been utilizing AI to enhance scientific discovery in domains such as biology, medicine, chemistry, and public health.
From the theory of why deep networks work to training methods for today's largest models.
Self-play fine-tuning, preference optimization and alignment, efficient attention, and optimizers for training large models.
Provably efficient and minimax-optimal algorithms for RL and bandits.
Generalization, benign overfitting and optimization of over-parameterized networks.
Variance reduction, saddle-point escape and lower bounds for stochastic optimization.
Diffusion and generative models for biology, medicine, chemistry and public health.
A few recent papers. The full list of 260+ is on the publications page.
We are oragnizing the New Frontiers of AI for Drug Discovery and Development at NeurIPS 2023.
Senior Area Chair for NeurIPS 2023, Area Chair for ICLR 2024, AISTATS 2024, AAAI 2024