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/TAO YU
// PERSON

Tao Yu

ROLE LAB DIRECTOR, XLANG LABAT HONG KONG UNIVERSITYMENTIONS 3LAST SEEN MAY 28, 2026
// BIO

Tao Yu is an Assistant Professor of Computer Science at the University of Hong Kong and Director of XLANG Lab (Executable Language Grounding Lab). His research focuses on grounding language and perception into executable actions for both digital and physical environments, with particular emphasis on embodied AI agents and Vision-Language-Action policies for robotics. He is best known for contributions including FineVLA, a framework for fine-grained instruction alignment in steerable robot policies, and has received the Google Research Scholar Award (2023) and Amazon Research Award (2022).

// RECENT MENTIONS
// SIGNALS
3 SIGNALS
01
product·arXiv Physical AI·MAY 28, 2026

FineVLA: Fine-Grained Instruction Alignment for Steerable Vision-Language-Action Policies

Source
02
product·arXiv Physical AI·MAY 28, 2026

The authors release FineVLA-Tool (the pipeline to unify and annotate datasets), FineVLA-Data (47,159 human-verified trajectories), RoboFine-VLM (a specialized video annotator), and RoboFine-Bench (a benchmark for evaluating execution-level understanding).

Source
03
mention·arXiv Physical AI·MAY 28, 2026

Yu leads XLANG Lab, which has produced multiple influential works in language-grounded robotics and code/agent systems. His lab's focus on open-source infrastructure for embodied AI makes FineVLA a flagship contribution to the field.

Source

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