Entertain, then Cancel: How Thinking Makes Reasoning Models Read Some and Or Literally
Paper • 2610.21204 • Published • 13
GeroldBurno
SebastianScott98
AI & ML interests
None yet
Recent Activity
upvoted a paper about 17 hours ago
Entertain, then Cancel: How Thinking Makes Reasoning Models Read Some and Or Literally upvoted a paper about 17 hours ago
PACE: Periodic and Channel-Aligned Encoding of Four-Bit Recurrent States upvoted a paper about 17 hours ago
Building AI Research Teams for Autonomous Discovery of Linear Attention ArchitecturesOrganizations
None yet
upvoted 4
papers about 17 hours ago
PACE: Periodic and Channel-Aligned Encoding of Four-Bit Recurrent States
Paper • 2610.29545 • Published • 20
Building AI Research Teams for Autonomous Discovery of Linear Attention Architectures
Paper • 2610.28887 • Published • 17
DONIC: Generalist Dexterous Bimanual Tracking Control from Human Demonstrations
Paper • 2610.29997 • Published • 142
upvoted 3
papers 2 days ago
Sparse Feature Policy Unlearning Mitigates State Hallucination in Vision-Language-Action Models
Paper • 2610.09496 • Published • 7
Learning to Discriminate Scene Structures Makes Self-Supervised Depth Learning Scalable
Paper • 2610.23600 • Published • 13
Holi-World: Building Holistic World Intelligence from Human-Ego Experience
Paper • 2610.26549 • Published • 173