🔥 News

• 2025.12: 🔥 Release 🎩 DraCo: Draft as CoT for Text-to-Image Preview and Rare Concept Generation, an interleaved reasoning framework for improved image generation.
• 2025.10: 🔥 Release Are Video Models Ready as Zero-Shot Reasoners? An Empirical Study with the MME-CoF Benchmark., an empirical study on the zero-shot reasoning capabilities of video models.
• 2025.10: 🔥 Release UlmEvalkit, an open-source toolkit for evaluating unified MLLMs and generative models for image generation tasks.
• 2025.09: 🎉 Three papers (T2I-R1, MINT-CoT, and BLINK-Twice) are accepted by NeurIPS 2025.
• 2025.05: 🎉 Two papers (MME-CoT and EasyRef) are accepted by ICML 2025.
• 2025.01: 🎉 One paper (MMSearch) is accepted by ICLR 2025.