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/JIAMING LIU
// PERSON

Jiaming Liu

ROLE PROJECT LEADAT PEKING UNIVERSITYMENTIONS 2LAST SEEN APRIL 30, 2026
// BIO

Project lead on LaST-R1, building a sustained research program on latent reasoning for VLA models at Peking University.

// RECENT MENTIONS
// SIGNALS
2 SIGNALS
01
product·arXiv Physical AI·APRIL 30, 2026

LaST-R1 jointly trains both the reasoning process and the action output, using environment rewards to shape the robot's internal 'thinking' in latent space.

Source
02
mention·arXiv Physical AI·APRIL 30, 2026

LaST-R1 is a follow-on to LaST_0 (arXiv:2601.05248), suggesting this is a multi-paper research agenda, not a one-off result.

Source

AI-extracted from podcast / newsletter / paper summaries. May contain errors.

Jiaming Liu — 2 mentions on Teahose