Entertain, then Cancel: How Thinking Makes Reasoning Models Read Some and Or Literally Paper • 2610.21204 • Published 14 days ago • 23
PACE: Periodic and Channel-Aligned Encoding of Four-Bit Recurrent States Paper • 2610.29545 • Published 8 days ago • 24
Building AI Research Teams for Autonomous Discovery of Linear Attention Architectures Paper • 2610.28887 • Published 9 days ago • 45
DONIC: Generalist Dexterous Bimanual Tracking Control from Human Demonstrations Paper • 2610.29997 • Published 8 days ago • 162
Sparse Feature Policy Unlearning Mitigates State Hallucination in Vision-Language-Action Models Paper • 2610.09496 • Published 22 days ago • 7
Learning to Discriminate Scene Structures Makes Self-Supervised Depth Learning Scalable Paper • 2610.23600 • Published 13 days ago • 13
Holi-World: Building Holistic World Intelligence from Human-Ego Experience Paper • 2610.26549 • Published 10 days ago • 173
ComBodied Agents: a New Paradigm of Human-Centric Agentic AI Paper • 2608.10915 • Published Aug 11 • 195