// PERSON
Zhongyuan Liao
ROLE LEAD AUTHORAT HONG KONG UNIVERSITY OF SCIENCE AND TECHNOLOGYMENTIONS 2LAST SEEN MAY 18, 2026
// BIO
Lead author of TacSE3 paper, based at HKUST, with background in physics-grounded tactile perception.
// RECENT MENTIONS
// SIGNALS
2 SIGNALS
01
product·arXiv Physical AI·MAY 18, 2026
“TacSE3 uses fingertip tactile sensors to detect and measure exactly how the object is moving inside the grip, then feeds that signal back to correct the robot's actions in real-time, without retraining the underlying policy.”
Source→02
mention·arXiv Physical AI·MAY 18, 2026
“the method performs well on smooth and weak-texture objects such as the large sphere (2.9°), ellipsoidal object (3.6°), cylindrical object (2.8°), and wooden cube (3.2°), indicating that accurate rotation estimation does not depend on distinctive tactile texture.”
Source→AI-extracted from podcast / newsletter / paper summaries. May contain errors.