DONIC: Generalist Dexterous Bimanual Tracking Control from Human Demonstrations Paper • 2610.29997 • Published 9 days ago • 162
DeLoop: Repeated Actions as Self-Supervision for Long-Horizon Agents Paper • 2610.19376 • Published 16 days ago • 34
WorldStream: Streaming Interactive 3D Worlds with Hierarchical Planning and Persistent State Paper • 2610.28827 • Published 10 days ago • 21
RubatoCodec: Budgeted Adaptive Speech Tokenization with Streaming Decoding Paper • 2610.29434 • Published 9 days ago • 15
EgoXperience: Learning World-Grounded Egocentric Representations from Human Experience Paper • 2610.26625 • Published 11 days ago • 189
Policy Is Not Capability: Some Safety Benchmarks Measure Which Definition of "Unsafe" You Trained On Paper • 2610.25060 • Published 12 days ago • 18
Holi-World: Building Holistic World Intelligence from Human-Ego Experience Paper • 2610.26549 • Published 11 days ago • 173
ComBodied Agents: a New Paradigm of Human-Centric Agentic AI Paper • 2608.10915 • Published Aug 11 • 195