Mulberry. [NIPS'25 Spotlight] Mulberry, an o1-like Reasoning and Reflection MLLM Implemented via Collective MCTS
1.2kAwesome-Agentic-MLLMs. Agentic MLLMs
215DenseConnector. 【NeurIPS 2024】Dense Connector for MLLMs
183Awesome-Reasoning-MLLM. Awesome Reasoning in MLLMs: Papers and Projects about learning to reason with MLLMs, including Chain-of-Thought (CoT), OpenAl o1, and DeepSeek-R1
63Side4Video. Python
42R1-ShareVL. [NeurIPS 2025] Reasoning MLLM, Share-GRPO, advantage vanishing, sparse reward
38MM-DeepResearch. MLLM, DeepResearch, Agentic AI
17MMReason. [ICCV 2025] MMReason, MLLMs, step by step, reasoning benchmark, AGI
15