rayruiyang/VST-3B-RL
Image-Text-to-Text • 4B • Updated • 301 • 3
VST
A comprehensive framework designed to cultivate VLMs with human-like visuospatial abilities.
-
-
rayruiyang/VST-3B-SFT
Image-Text-to-Text • 4B • Updated • 90 -
rayruiyang/VST-7B-SFT
Image-Text-to-Text • 8B • Updated • 84 -
rayruiyang/VST-7B-RL
Image-Text-to-Text • 8B • Updated • 91 -
Visual Spatial Tuning
Paper • 2511.05491 • Published • 53 -
rayruiyang/vst_3d_grounding_benchmark
Preview • Updated • 24 -
rayruiyang/vst_500k
Viewer • Updated • 563k • 4.22k • 4