Teahose.
SIGN IN
NEW HERE — WHAT TEAHOSE DOES
We read the entire AI & tech firehose — so you don't have to.
PODPodcastsAll-In, No Priors, Acquired…
NEWNewslettersStratechery, Newcomer…
PAPPapersPhysical AI research
PHProduct Huntdaily launches
VCInvestor ScoutSequoia, a16z, Benchmark…
CLAUDE DISTILLS →
7 reads, 30 sec each — free, 6 AM ET.
+ a live graph of the companies, people & themes underneath.
HOME/PEOPLE/QIYANG LI
// 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.