// PERSON
Senyu Fei
AT ARXIV PHYSICAL AIMENTIONS 1LAST SEEN JULY 5, 2026
// BIO
Senyu Fei is a PhD student at the Shanghai Innovation Institution whose research focuses on Vision-Language-Action models for robotics. He is best known for his work on LIBERO-Plus, a benchmark that reveals critical robustness vulnerabilities in state-of-the-art robotic manipulation models by testing their sensitivity to perturbations like camera viewpoints and initial states. His recent publications also include PokeVLA and SRPO, which further explore policy optimization and world knowledge guidance for VLA models.
// RECENT MENTIONS
// SIGNALS
1 SIGNAL
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→AI-extracted from podcast / newsletter / paper summaries. May contain errors.