SafeAtlas-VL: Beyond Binary Multimodal Safety with Large-Scale Data and Guard Models Paper • 2608.29098 • Published 27 days ago • 10
H2R-Bench: Benchmarking Human-to-Robot Manipulation Video Generation in World Models Paper • 2608.13049 • Published Aug 13 • 21
Reason, Then Re-reason: Cross-view Revisiting Improves Spatial Reasoning Paper • 2606.11683 • Published Jun 10 • 31