RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversations Paper • 2610.01780 • Published 10 days ago • 279
Receiver-Conditioned Latent Communication gives 94% CacheBack Paper • 2609.32046 • Published 16 days ago • 12
Skill2Real: Agentic Skill Learning for Zero-Shot Sim-to-Real Robot Manipulation Paper • 2610.02788 • Published 9 days ago • 18
Latent-MOPD: Latent Multi-Teacher On-Policy Distillation Paper • 2610.02381 • Published 10 days ago • 70
Spatial Memory Intelligence: Endowing World Models with Understanding-Driven Long-Term Memory Paper • 2610.02521 • Published 10 days ago • 59
Scaling Properties of Same-Family On-Policy Distillation Paper • 2609.32722 • Published 15 days ago • 326
Anisotropic Representations Improve Planning in JEPA World Models Paper • 2609.37441 • Published 12 days ago • 35
Follow the Entities: A Corpus Map for Agentic Search Paper • 2609.37226 • Published 12 days ago • 100
MaLiang-Harness: A Programmable Path to Image and Video Generation Paper • 2609.34309 • Published 13 days ago • 394