SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning Paper • 2606.13673 • Published Jun 11 • 111
OpenVoxel: Training-Free Grouping and Captioning Voxels for Open-Vocabulary 3D Scene Understanding Paper • 2601.09575 • Published Jan 14 • 26
Fast-ThinkAct: Efficient Vision-Language-Action Reasoning via Verbalizable Latent Planning Paper • 2601.09708 • Published Jan 14 • 56
4D-RGPT: Toward Region-level 4D Understanding via Perceptual Distillation Paper • 2512.17012 • Published Dec 18, 2025 • 49