GST-VLA: Structured Gaussian Spatial Tokens for 3D Depth-Aware Vision-Language-Action Models
Paper • 2603.09079 • Published • 1
Md Selim Sarowar
selim-sarowar
·
AI & ML interests
Vision Language Action Models, World Models, 5D Robot Manipulation, 3D Computer Vision
Recent Activity
liked a dataset 14 days ago
RajatDandekar/so101_box_to_bowl_v2 liked a dataset 14 days ago
RajatDandekar/so101_box_to_bowl authored a paper about 1 month ago
Explainable Parkinsons Disease Gait Recognition Using Multimodal RGB-D Fusion and Large Language ModelsOrganizations
None yet
upvoted 4
papers about 1 month ago
Unified Vision-Language-Action Model
Paper • 2506.19850 • Published • 28
Fast-ThinkAct: Efficient Vision-Language-Action Reasoning via Verbalizable Latent Planning
Paper • 2601.09708 • Published • 55
VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Model
Paper • 2602.10098 • Published • 19