See2Think: Do Multimodal Models Really Use Intermediate Visual States?
Paper • 2607.26769 • Published • 21
LauvAri
LauvAri
AI & ML interests
None yet
Recent Activity
upvoted a paper about 10 hours 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 Generation upvoted a paper 9 months ago
VCode: a Multimodal Coding Benchmark with SVG as Symbolic Visual
RepresentationOrganizations
None yet