Self-Distilling Future Video Representations for World Action Models Paper • 2610.30320 • Published 5 days ago • 37
When Do Biological Reasoning Models Use Their Biological Inputs? Paper • 2610.00898 • Published 25 days ago • 15
WebFovea: When the Model Is Right but the Click Is Wrong -- Reliable Round Trips for Vision-Based Web Agents on Live Websites Paper • 2610.03036 • Published 19 days ago • 20
Video DeltaNet: A Video-Native Hybrid Attention for Livestream Video Generation Paper • 2609.20744 • Published Sep 17 • 54
Continual Learning Mechanisms Compose for Long-Horizon Memorization Paper • 2609.06986 • Published Sep 7 • 371
MetroLLM-Bench: Evaluating Language Models as Transit Kiosk Runtimes Paper • 2609.10016 • Published Sep 9 • 29