SafeAtlas-VL: Beyond Binary Multimodal Safety with Large-Scale Data and Guard Models Paper • 2608.29098 • Published 16 days ago • 9
Learn What's Left, Not What's Mastered: Saturation Aware Advantage Reweighting for Multi-Reward Policy Optimization Paper • 2608.16072 • Published 28 days ago • 151
ABot-World-0: Infinite Interactive World Rollout on a Single Desktop GPU Paper • 2607.19191 • Published Jul 21 • 313