Emergence of Human to Robot Transfer in Vision-Language-Action Models

Exploring how transfer from human videos to robotic tasks emerges in robotic foundation models as they scale.

Emergence of Human to Robot Transfer in Vision-Language-Action Models Emergence of Human to Robot Transfer in VLAs Published December 16, 2025 Email research@physicalintelligence.company Simar Kareer, Karl Pertsch, James Darpinian, Judy Hoffman, Danfei Xu, Sergey Levine, Chelsea Finn, Suraj Nair Paper human_to_robot.pdf Loading… Loading… Loading… Loading… Loading… Loading… Loading… Loading… Loading… Loading… Loading… Loading… Loading… Loading… Loading… Loading… HUMAN DATA DIVERSE AND LARGE SCALE ROBOT DATA NEW ROBOT CAPABILITIES Loading… Loading… Loading… Loading… Loading… Loading… Loading… Lo

saved by

• Anson Yu
• abinaya dinesh
• HudZah
• Aaron Pham

related reading

• Emergence of Human to Robot Transfer in Vision-Language-Action Modelsphysicalintelligence.company
• Generalist - GEN-0 / Embodied Foundation Models That Scale with Physical Interactiongeneralistai.com
• how we accidentally solved robotics by watching 1 million hours of YouTube – atharva's blogksagar.bearblog.dev
• State of Vision-Language-Action (VLA) Research at ICLR 2026 – Moritz Reussmbreuss.github.io
• Causal Video Models Are Data-Efficient Robot Policy Learners | Rhoda AIrhoda.ai
• State of Robot Learning, December 2025vedder.io
• [2506.09985] V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planningarxiv.org
• EgoScaleresearch.nvidia.com
• A Steerable Model with Emergent Capabilitiespi.website
• [2602.10556] LAP: Language-Action Pre-Training Enables Zero-shot Cross-Embodiment Transferarxiv.org
• [2509.22407] EMMA: Generalizing Real-World Robot Manipulation via Generative Visual Transferarxiv.org
• 45d74e190008c7bff2845ffc8e3facd3-Paper-Conference.pdfproceedings.iclr.cc