VideoJev: System One Model for Video Understanding and Interaction Paper • 2610.18615 • Published 12 days ago • 342
Transformers Stop Thinking Too Early, and a Tiny LoRA Fixes It Paper • 2609.36585 • Published 26 days ago • 42
False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents Paper • 2609.39102 • Published 25 days ago • 235
The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation Paper • 2609.36484 • Published 26 days ago • 208