OpenVoxel: Training-Free Grouping and Captioning Voxels for Open-Vocabulary 3D Scene Understanding Paper • 2601.09575 • Published 4 days ago • 24
Fast-ThinkAct: Efficient Vision-Language-Action Reasoning via Verbalizable Latent Planning Paper • 2601.09708 • Published 4 days ago • 48
4D-RGPT: Toward Region-level 4D Understanding via Perceptual Distillation Paper • 2512.17012 • Published about 1 month ago • 43