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/XINGHANG LI
// PERSON

Xinghang Li

ROLE CO-CORRESPONDING AUTHORAT XIAOMI ROBOTICSMENTIONS 2LAST SEEN APRIL 29, 2026
// BIO

Xinghang Li is a PhD student in the Department of Computer Science and Technology at Tsinghua University and a researcher at Xiaomi Robotics, where he bridges academic world-model research and industrial robotics. He is best known as a co-corresponding author of X-WAM (Unified 4D World Action Modeling from Video Priors with Asynchronous Denoising), a system that is the first to unify real-time robotic control, photorealistic 4D video generation, and 3D spatial reconstruction within a single model pretrained on over 5,800 hours of robotic data. His broader research focuses on vision-language-action models, large-scale robot learning, and connecting visual pretraining with robotic manipulation.

// RECENT MENTIONS
// SIGNALS
2 SIGNALS
01
product·arXiv Physical AI·APRIL 29, 2026

A Xiaomi Robotics / Tsinghua team has built the first system to simultaneously do real-time robot control, spatially-accurate 3D reconstruction, and photorealistic video prediction from a *single* model — trained on 5,800+ hours of robot data.

Source
02
mention·arXiv Physical AI·APRIL 29, 2026

As co-corresponding author at Xiaomi Robotics, Li is a key figure in translating world-model research into deployed hardware products.

Source

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