Latest

• Inference-Time Policy Steering through Human Interactions
• TWIN: Two-handed Intelligent Benchmark for Bimanual Manipulation
• Latent Action Pretraining from Videos
• Proto-CLIP: Vision-Language Prototypical Network for Few-Shot Learning
• RVT-2: Learning Precise Manipulation from Few Demonstrations
• SKT-Hang: Hanging Everyday Objects via Object-Agnostic Semantic Keypoint Trajectory Generation
• SynH2R: Synthesizing Hand-Object Motions for Learning Human-to-Robot Handovers
• RVT: Robotic View Transformer for 3D Object Manipulation
• SCONE: A Food Scooping Robot Learning Framework with Active Perception
• AnyTeleop: A General Vision-Based Dexterous Robot Arm-Hand Teleoperation System
• FewSOL: A Dataset for Few-Shot Object Learning in Robotic Environments
• Learning Human-to-Robot Handovers from Point Clouds
• Learning Robust Real-World Dexterous Grasping Policies via Implicit Shape Augmentation
• Learning Perceptual Concepts by Bootstrapping from Human Queries
• IFOR: Iterative Flow Minimization for Robotic Object Rearrangement
• HandoverSim: A Simulation Framework and Benchmark for Human-to-Robot Object Handovers
• Model Predictive Control for Fluid Human-to-Robot Handovers
• DexYCB: A Benchmark for Capturing Hand Grasping of Objects
• Reactive Human-to-Robot Handovers of Arbitrary Objects
• Learning to Sit: Synthesizing Human-Chair Interactions via Hierarchical Control
• DexPilot: Depth-Based Teleoperation of Dexterous Robotic Hand-Arm System
• Motion Reasoning for Goal-Based Imitation Learning