Shunlin Lu
Shunlin Lu is a PhD student in computer science at The Chinese University of Hong Kong, Shenzhen, and a research intern at Shanghai AI Lab. His research focuses on embodied AI, character animation, and foundation models for humanoid robots. He is known for co-developing MotionStreamer, leading the Motion-X large-scale motion dataset, and co-creating MotionLLM for motion understanding. He serves as a project lead on the N0-VTLA and N0-TWAM vision-tactile-language-action models for contact-rich robotic manipulation.
“N0-VTLA is, by its own claim, the first vision-tactile-language-action model pretrained on tactile data at scale. The result: on a 20-task simulation suite, N0-VTLA reaches 63.8% mean success against 44.0% for the strongest baseline (π0.5), and wins all nine real-robot NeoReal tasks”
Source→“Shunlin Lu: Project Lead and contributor across pretraining, offline RL, and post-training”
Source→AI-extracted from podcast / newsletter / paper summaries. May contain errors.