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/LI JI
// PERSON

Li Ji

AT ARXIV PHYSICAL AIMENTIONS 1LAST SEEN JULY 5, 2026
// BIO

Ji Li is a researcher who has published extensively on robotics and physical AI, with work appearing on arXiv covering topics such as world models for physical AI, robot policy learning, and action chunking for robot control. Their publications include collaborations on projects like Cosmos 3, Dexterity-BEV, and Qwen-VLA, which address vision-language-action modeling and generalizable robot policies. They are affiliated with arXiv-related research in physical AI and robotics.

// RECENT MENTIONS
// SIGNALS
1 SIGNAL
01
product·arXiv Physical AI·JULY 5, 2026

ICWM enables robot policies to autonomously infer essential system variables from a short history of self-generated, task-agnostic interactions.

Source

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