Video-MME-Logical: A Controlled Diagnostic Benchmark for Video Temporal-Logical Reasoning Paper • 2606.27828 • Published 29 days ago • 25
Hy-Embodied-0.5-VLA: From Vision-Language-Action Models to a Real-World Robot Learning Stack Paper • 2606.14409 • Published Jun 12 • 15
Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players Paper • 2605.28816 • Published May 27 • 433