VASPO: Self-Distillation with Privileged Value Estimation Paper • 2610.20516 • Published 3 days ago • 8
Thinking Inertia: LLMs Keep Thinking When Told Not To Paper • 2610.11765 • Published 9 days ago • 248
OSWorld-Pro: Process-based Evaluation for Computer Use Agents Paper • 2609.24890 • Published 26 days ago • 28
EditHero: A Benchmark for Long-Horizon Part-Level 3D Editing and Vibe Modeling Paper • 2610.02298 • Published 16 days ago • 60
JEPA-Anything: Learning Predictive Models across Different Worlds Paper • 2609.20800 • Published about 1 month ago • 79
RoboSPA: Can VLA Models Go Beyond Simple Scenes and Short-Horizon Tasks? Paper • 2609.05324 • Published Sep 4 • 28