RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversations Paper • 2610.01780 • Published 28 days ago • 299
Science or Slop?: Benchmarking and Mitigating Scientific Slop in AI-Generated Papers Paper • 2610.00531 • Published 29 days ago • 63
EngiWorld: What Can Frontier Agents Deliver in Professional Engineering Environments? Paper • 2609.37686 • Published 30 days ago • 75
SAKI: Maximal-Coupling-Routed Teacher Supervision for On-Policy Distillation Paper • 2609.36601 • Published 30 days ago • 94
LEGO-Anything: Coding Agents for 3D Scene Reconstruction Paper • 2609.36380 • Published about 1 month ago • 104
PanoVLN: Towards Effective Panoramic Vision-and-Language Navigation Paper • 2609.34759 • Published about 1 month ago • 93