OpenART: Scaling Agent Red Teaming via Open-Ended Environment Evolution Paper • 2608.00677 • Published 15 days ago • 252
SkillZip: Evaluation-Free Skill Compression for Self-Evolving Agents by Discovering Reusable Structure Paper • 2608.11079 • Published 5 days ago • 16
DyPES-VLA: Learning Shared Dynamics Priors and Embodiment-Specific Control for Cross-Embodiment Manipulation Paper • 2608.06374 • Published 10 days ago • 23
Poplar: A Scalable Pipeline for Human-Centric Image Dataset Synthesis Paper • 2608.00440 • Published 15 days ago • 10