RESOURCE2SKILL: Distilling Executable Agent Skills from Human-Created Multimodal Resources Paper β’ 2606.29538 β’ Published Jul 16 β’ 145
Running on Zero Agents Featured 1.48k Omni Video Factory π 1.48k text to video, image to video, video extend
Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representations Paper β’ 2510.23607 β’ Published Oct 27, 2025 β’ 181