See2Think: Do Multimodal Models Really Use Intermediate Visual States?
Paper • 2607.26769 • Published • 21
Latent Lai
Latent123
AI & ML interests
None yet
Recent Activity
upvoted a paper about 8 hours ago
See2Think: Do Multimodal Models Really Use Intermediate Visual States? upvoted a paper 9 months ago
VCode: a Multimodal Coding Benchmark with SVG as Symbolic Visual
RepresentationOrganizations
None yet
upvoted a paper about 8 hours ago