TARS: Timestep-Aware Data Scaling for 3D-Free Video Re-Shooting Paper • 2607.28261 • Published 8 days ago • 116
Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading Paper • 2607.08964 • Published 29 days ago • 77
SkillHone: A Harness for Continual Agent Skill Evolution Through Persistent Decision History Paper • 2606.08671 • Published Jun 23 • 46
Imaginative Perception Tokens Enhance Spatial Reasoning in Multimodal Language Models Paper • 2606.03988 • Published Jun 3 • 126