Kuo-Han Hung
Kuo-Han Hung is a Computer Science Master's student at Stanford University, where he conducts research in robotics and embodied AI. He is a co-author on EXPO-FT, a system for sample-efficient reinforcement learning fine-tuning of vision-language-action models, and has published work on imitation learning, dexterous manipulation, and robot policy reliability at venues including NeurIPS and ICLR. His research focuses on developing robot policies that are more generalizable and reliable for real-world deployment.
“Stanford researchers have cracked a critical bottleneck in physical AI deployment: how to take a pretrained robot foundation model and push it to 100% task reliability in under 20 minutes of real robot time.”
Source→“Contact listed as {perryd, khhung}@stanford.edu; equal contribution noted on the paper.”
Source→AI-extracted from podcast / newsletter / paper summaries. May contain errors.