JarvisHub: An Open Harness for Canvas-Native Multimodal Creative Agents Paper • 2607.23588 • Published 4 days ago • 114
RESOURCE2SKILL: Distilling Executable Agent Skills from Human-Created Multimodal Resources Paper • 2606.29538 • Published 14 days ago • 141
NANO3D: A Training-Free Approach for Efficient 3D Editing Without Masks Paper • 2510.15019 • Published Oct 16, 2025 • 65