Nanjing University
DiffThinker. [ICML 2026] Official repo for "DiffThinker: Towards Generative Multimodal Reasoning with Diffusion Models"
185GEMS. GEMS: Agent-Native Multimodal Generation with Memory and Skills
138FrameThinker. [ICLR 2026] Official repo for "FrameThinker: Learning to Think with Long Videos via Multi-Turn Frame Spotlighting"
50VideoSSR. [CVPR 2026] Official repo for "VideoSSR: Video Self-Supervised Reinforcement Learning"
40