Yao Mu
Yao Mu is a tenure-track Assistant Professor in the School of Computer Science at Shanghai Jiao Tong University, where he leads research on multimodal embodied intelligence and robot learning. He received his Ph.D. from the Department of Computer Science at The University of Hong Kong and has held visiting positions at ETH Zurich and the National University of Singapore. He is best known for his work on vision-language-action model post-training and dexterous robot manipulation, including co-authorship on BORA, a framework that bridges offline reinforcement learning and online residual adaptation to close the execution gap for high-dimensional dexterous hand policies. He has published over 50 papers in top venues including NeurIPS, ICML, RSS, and IJRR, and serves as an Area Chair for ICLR.
“BORA solves a critical bottleneck in deploying dexterous robot hands — the gap between a VLA model that 'understands' a task visually and one that can actually execute it reliably with 20+ fingers and joints in the real world. It achieves an 86% average success rate on five real-world dexterous tasks, up from ~53% with pure imitation learning.”
Source→“a 33% absolute increase in average success rate and up to a 43% improvement in unseen object generalization.”
Source→“Corresponding author on the BORA framework, which achieves 'a 33% absolute increase in average success rate and up to a 43% improvement in unseen object generalization.'”
Source→AI-extracted from podcast / newsletter / paper summaries. May contain errors.