Research
PDRVLA adds physical dynamics representations to a vision-language-action robot model
PDRVLA uses a lightweight module to extract physical tokens without online video generation, reporting 99.3% on LIBERO, 89.9% on LIBERO-Plus, 93.6% on RoboTwin 2.0 and 81.5% on SimplerEnv in simulation.
Every outlet that ran it 1 article
Hugging Face PapersResearchLead
PDRVLA: A Vision-Language-Action Model with Physical Dynamics Representations