See2Think: Do Multimodal Models Really Use Intermediate Visual States?
Paper • 2607.26769 • Published • 22
👋 Open to Work
Jason Cai
WaterCoFire
·
AI & ML interests
None yet
Recent Activity
upvoted a paper 1 day ago
See2Think: Do Multimodal Models Really Use Intermediate Visual States? upvoted a paper about 1 month ago
DataEvolver: Self-Evolving Multi-Agent Data Construction for Text-Rich Image GenerationOrganizations
upvoted a paper 1 day ago