RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversations Paper • 2610.01780 • Published 17 days ago • 288
Rollout-Marginal Distillation for Long-Horizon Autoregressive Video Generation Paper • 2609.37925 • Published 19 days ago • 23
HelixWorld: A Real-time Interactive Audio-Visual World Model Paper • 2609.38123 • Published 19 days ago • 38
Rethinking Latent Visual Reasoning: Grounding Latent Reasoning in Visual Evidence Paper • 2609.34563 • Published 20 days ago • 223
SkillGym: Training Skill-Use Agents with Automatic Verifiable Environment Generation Paper • 2609.37539 • Published 19 days ago • 13
LEAP: Learned Block-wise Evidence Retrieval for Long Audio-Video Perception Paper • 2609.39938 • Published 18 days ago • 3