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/TZU-YUAN LIN
// PERSON

Tzu-Yuan Lin

ROLE RESEARCHERAT UNIVERSITY OF MICHIGANMENTIONS 1LAST SEEN MAY 14, 2026
// BIO

Tzu-Yuan Lin is a postdoctoral associate in the Biomimetic Robotics Lab at the Massachusetts Institute of Technology, advised by Professor Sangbae Kim. He earned his Ph.D. in Robotics from the University of Michigan under the supervision of Professor Maani Ghaffari, where his research focused on the intersection of machine learning and robot perception. He is best known for developing proprioceptive invariant robot state estimation methods for legged robots, including the DRIFT open-source InEKF library and learning-based contact estimation techniques.

// RECENT MENTIONS
// SIGNALS
1 SIGNAL
01
mention·arXiv Physical AI·MAY 14, 2026

Lin et al. proposed augmenting the state-of-the-art invariant extended Kalman filter (InEKF) with learned contact detection. However, this approach requires labeled contact data for training and still treats contact as a binary state.

Source

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