// PERSON
Yehao Lu
ROLE LEAD AUTHORMENTIONS 2LAST SEEN AUGUST 26, 2026
// BIO
Yehao Lu is a researcher affiliated with Zhejiang University who has served as a research intern at AGIBOT, contributing to robotic foundation models. He is known for lead-author work on vision-language-action models and object detection, including V-Link and Dynamic-DINO, as well as research on image-to-video diffusion models and bird's-eye-view 3D object detection. His publications span top computer vision conferences such as CVPR, ICCV, and AAAI.
// RECENT MENTIONS
// SIGNALS
2 SIGNALS
01
product·arXiv Physical AI·AUGUST 26, 2026
“V-Link: Recovering Lost Visual Representations in Action DiT for Vision-Language-Action Models”
Source→02
hire·arXiv Physical AI·AUGUST 26, 2026
“Work done as a research intern at AGIBOT. Yehao Lu, Lead author, affiliated with Zhejiang University and AGIBOT.”
Source→AI-extracted from podcast / newsletter / paper summaries. May contain errors.