VASPO: Self-Distillation with Privileged Value Estimation Paper • 2610.20516 • Published 2 days ago • 7
SpaceCast-Bench: Evaluating Predictive Spatial Reasoning in Vision-Language Models Paper • 2610.12402 • Published 8 days ago • 14
HyperBrowseComp: A Multilingual and Multimodal Stress Test for Web-Browsing Agents Paper • 2610.03574 • Published 14 days ago • 60
Continual Learning Mechanisms Compose for Long-Horizon Memorization Paper • 2609.06986 • Published Sep 7 • 376