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 about 16 hours ago
TriAttention: Efficient Long Reasoning with Trigonometric KV Compression upvoted a paper 6 days ago
ViGoR-Bench: How Far Are Visual Generative Models From Zero-Shot Visual Reasoners? upvoted a paper 8 days ago
MolmoPoint: Better Pointing for VLMs with Grounding TokensOrganizations
None yet
models 6
rayruiyang/VST-3B-SFT
Image-Text-to-Text • 4B • Updated • 693
rayruiyang/VST-3B-RL
Image-Text-to-Text • 4B • Updated • 37 • 3
rayruiyang/VST-7B-RL
Image-Text-to-Text • 8B • Updated • 162
rayruiyang/VST-7B-SFT
Image-Text-to-Text • 8B • Updated • 824
rayruiyang/Haplo-8B-MI-672
8B • Updated
rayruiyang/Haplo-8B-672
8B • Updated • 2 • 1