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/SIYIN WANG
// PERSON

Siyin Wang

AT ARXIV PHYSICAL AIMENTIONS 2LAST SEEN JULY 5, 2026
// BIO

Siyin Wang is a PhD student at Fudan University advised by Professor Xipeng Qiu, affiliated with the Fudan NLP Lab and the Shanghai Innovation Institute. Her research focuses on language intelligence, large language model alignment, multimodality, and embodied AI. She is known for her work on Vision-Language-Action models and In-Context World Modeling, a framework that enables robot policies to adapt to novel configurations by inferring system variables from self-generated interactions without parameter updates.

// RECENT MENTIONS
// SIGNALS
2 SIGNALS
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
02
mention·arXiv Physical AI·JULY 5, 2026

ICWM treats it as a system identification problem solved through in-context learning

Source

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

Siyin Wang · arXiv Physical AI — 2 mentions on Teahose