Inferring Forces and Learning Human Utilities From Videos

N/A

Inferring Forces and Learning Human Utilities From Videos Yixin Zhu1∗ Chenfanfu Jiang2∗ Yibiao Zhao1 Demetri Terzopoulos2 Song-Chun Zhu1 1 UCLA Center for Vision, Cognition, Learning and Autonomy 2 UCLA Computer Graphics & Vision Laboratory Abstract We propose a notion of affordance that takes into ac- count physical quantities generated when the…

saved by

• Umangi Jain

related reading

• Generative Image Dynamicsgenerative-dynamics.github.io
• TossingBot: Learning to Throw Arbitrary Objects with Residual Physicarxiv.org
• Emergence of Human to Robot Transfer in Vision-Language-Action Modelspi.website
• pdfopenreview.net
• Generating Robot Hands from Human Demonstrationsarxiv.org
• Learning 3D object-centric representation through predictionarxiv.org
• A Unified Model for Motion-Conditioned Robot Co-designtransformer-transformer.github.io
• [2207.13807] Pose-NDF: Modeling Human Pose Manifolds with Neural Distance Fieldsarxiv.org
• Deep Reinforcement Learning from Human Preferencesproceedings.neurips.cc
• [2506.09985] V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planningarxiv.org
• Superquadrics Revisited: Learning 3D Shape Parsing beyond Cuboidsarxiv.org
• [2501.12493] ELEGNT: Expressive and Functional Movement Design for Non-anthropomorphic Robotarxiv.org