Masking Teacher and Reinforcing Student for Distilling Vision-Language Models Paper • 2512.22238 • Published 23 days ago • 24
Quantile Rendering: Efficiently Embedding High-dimensional Feature on 3D Gaussian Splatting Paper • 2512.20927 • Published 23 days ago • 15
Fast-ThinkAct: Efficient Vision-Language-Action Reasoning via Verbalizable Latent Planning Paper • 2601.09708 • Published about 22 hours ago • 34
OpenVoxel: Training-Free Grouping and Captioning Voxels for Open-Vocabulary 3D Scene Understanding Paper • 2601.09575 • Published 1 day ago • 22
4D-RGPT: Toward Region-level 4D Understanding via Perceptual Distillation Paper • 2512.17012 • Published 28 days ago • 43