See2Think: Do Multimodal Models Really Use Intermediate Visual States? Paper • 2607.26769 • Published 4 days ago • 22
OmniOPD: Logit-Free On-Policy Distillation via Speculative Verification Paper • 2606.01476 • Published May 31 • 9
StableI2I: Spotting Unintended Changes in Image-to-Image Transition Paper • 2605.04453 • Published May 6 • 11
LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Calling Paper • 2511.20785 • Published Nov 25, 2025 • 188