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
• Nevedhaa Ayyappan
• Idhant Gulati
• Yash Karthik

related reading

• Emergence of Human to Robot Transfer in Vision-Language-Action Modelsphysicalintelligence.company
• EgoScaleresearch.nvidia.com
• Generalist - GEN-0 / Embodied Foundation Models That Scale with Physical Interactiongeneralistai.com
• A Steerable Model with Emergent Capabilitiespi.website
• Open X-Embodiment: Robotic Learning Datasets and RT-X Modelsarxiv.org
• State of Robot Learning, December 2025vedder.io
• Causal Video Models Are Data-Efficient Robot Policy Learners | Rhoda AIrhoda.ai
• [2506.09985] V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planningarxiv.org
• How Claude Performs on Robotics Tasks \ Anthropicanthropic.com
• [2509.22407] EMMA: Generalizing Real-World Robot Manipulation via Generative Visual Transferarxiv.org
• Dexterous Robotic Foundation Modelsyoutube.com
• A VLA with Open-World Generalizationpi.website