|
Vint Lee Hello! I'm a masters student in EECS at UC Berkeley, where I'm working on Machine Learning research under the mentorship of Pieter Abbeel, Youngwoon Lee, and John Wawrzynek. Previously, I completed my undergraduate studies in CS and Math at UC Berkeley. |
|
ResearchI'm interested in deep learning in general, and model-based RL and generative models in particular. |
|
Chip Placement with Diffusion
Vint Lee, Chun Deng, Leena Elzeiny, Pieter Abbeel, John Wawrzynek Preprint arXiv We train diffusion models to perform macro placement, an important step in designing chips, using our novel data-generation algorithm and model architecture. |
|
DreamSmooth: Improving Model-based Reinforcement Learning via Reward Smoothing
Vint Lee, Pieter Abbeel, Youngwoon Lee ICLR, 2024 project page / code / arXiv Reward smoothing provides significant improvement to performance of model-based RL algorithms in many sparse-reward environments. |
|
Low-cost, Lightweight Electronic Flow Regulators for Throttling Liquid Rocket Engines
Vint Lee, Sohom Roy IAC, 2023. Best Undergraduate Paper Award project page / code / arXiv Electronic pressure regulators enable more flexible and accurate control of pressures in liquid rocket engines, opening up new capabilities for collegiate teams such as throttling. |
|
Website template from Jon Barron. |