About
I am a Professor of the Graduate School, conducting research in the Berkeley AI Research (BAIR) lab. For the last 20 years, I have focused on making algorithms in the rapidly evolving areas of Machine Learning and AI more computationally efficient. Currently, I am focused on the computational challenges presented by Large Language Models and complex agentic systems. I invite postdoctoral fellows and PhD students with published research in these areas to apply to my group, but please refer to my personal webpage for details. Outstanding current Berkeley undergraduates are also invited to apply. I began my research career in industry where I developed efficient algorithms for logic synthesis and related areas. I have won many awards for that research, including “Most Influential Paper of the 1980’s” from the Design Automation Conference. I followed my early research to Synopsys where I became their first CTO. My approach to research is motivated by practical problems, and I always aspire to make a real-world impact with my work. As a result, our research group is entirely funded by industrial sponsors. Further, my orientation has naturally led me to an active engagement in entrepreneurship. I am currently a co-founder of Narada.ai and SigIQ.ai. Previously, I co-founded Deepscale (acquired by Tesla) and Nexusflow.ai (acquired by NVIDIA). I also serve as an investor, advisor, or both, to Perplexity.ai, Sima.ai, and many others.
Research Performance Summary
First Recorded Paper
The M-shuffle as an interconnection network for SIMD machines
Year: 1982
Citations: 7
Venue: Proceedings of 20th Allerton Conference on Communication, Control, and
Latest Recorded Paper
Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks
Year: 2025
Citations: 0
Venue: arXiv e-prints, arXiv: 2503.09572
Last 10 Years Publication Activity
This timeline shows the professor's yearly publication activity.