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/STEVEN OH
// PERSON

Steven Oh

ROLE PHD RESEARCHERAT CARNEGIE MELLON UNIVERSITYMENTIONS 2LAST SEEN JUNE 10, 2026
// BIO

Steven Oh is a robotics researcher who served as a visiting scholar at Carnegie Mellon University's Robotics Institute in the Pathak Research Group while completing his undergraduate studies in mechanical engineering at Waseda University. He is known for his work on hardware and learning for contact-rich manipulation, including co-authorship on CLAW, a soft wrist mechanism for robust robot manipulation, and FACTR 2, which introduces Neural External Torque Estimation for force-aware policy learning on commodity robot arms without dedicated force sensors. He is an incoming CS PhD student at the University of Chicago, advised by Professor Haozhi Qi.

// RECENT MENTIONS
// SIGNALS
2 SIGNALS
01
product·arXiv Physical AI·JUNE 10, 2026

NEXT (Neural External Torque Estimation) trains a small LSTM on 10 minutes of free-motion data — no contact, no labels, no force sensor required — and achieves external torque estimation accuracy of 0.547 ± 0.348 Nm L1 error during contact on a Franka arm

Source
02
mention·arXiv Physical AI·JUNE 10, 2026

Steven Oh | Carnegie Mellon University / Waseda University | Equal-contribution first author with a joint appointment, bringing hardware and contact dynamics expertise from Waseda.

Source

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