// PERSON
Qiyang Li
ROLE RESEARCHERAT UC BERKELEYMENTIONS 1LAST SEEN MAY 1, 2026
// BIO
Lead author on QAM (Q-Learning with Adjoint Matching); researcher at UC Berkeley working on flow-based RL for robotics.
// RECENT MENTIONS
// SIGNALS
1 SIGNAL
01
mention·arXiv Physical AI·MAY 1, 2026
“We thank Qiyang Li for helpful discussions... Li and Levine introduce QAM, using critic gradients to improve flow-based policies through adjoint matching, achieving stable training from scratch in simulation.”
Source→AI-extracted from podcast / newsletter / paper summaries. May contain errors.