A comprehensive framework designed to cultivate VLMs with human-like visuospatial abilities.
Ray Yang
rayruiyang
AI & ML interests
None yet
Recent Activity
upvoted a paper 1 day ago
MolmoPoint: Better Pointing for VLMs with Grounding Tokens upvoted a paper 6 days ago
ProAct: Agentic Lookahead in Interactive Environments updated a dataset 19 days ago
rayruiyang/vst_500kOrganizations
None yet
models 6
rayruiyang/VST-3B-SFT
Image-Text-to-Text • 4B • Updated • 734
rayruiyang/VST-3B-RL
Image-Text-to-Text • 4B • Updated • 55 • 3
rayruiyang/VST-7B-RL
Image-Text-to-Text • 8B • Updated • 144
rayruiyang/VST-7B-SFT
Image-Text-to-Text • 8B • Updated • 865
rayruiyang/Haplo-8B-MI-672
8B • Updated
rayruiyang/Haplo-8B-672
8B • Updated • 1 • 1