Awesome-Multimodal-Reasoning

Contributions are most welcome, if you have any suggestions or improvements, feel free to create an issue or raise a pull request.

Contents

• Benchmark
• Supervised Fine-Tuning
• Reinforcement Learining
• SFT + RL

Multimodal Reasoning Benchmark

Supervised Fine-Tuning

Image MLLM

• Virgo: A Preliminary Exploration on Reproducing o1-like MLLM

Video MLLM

Reinforcement Learining

Image MLLM

• InternLM-XComposer2.5-Reward: A Simple Yet Effective Multi-Modal Reward Model
• Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization
• MM-RLHF: The Next Step Forward in Multimodal LLM Alignment

Video MLLM

• Temporal Preference Optimization for Long-Form Video Understanding

SFT+RL

Image MLLM

• Improve Vision Language Model Chain-of-thought Reasoning

Video MLLM

• Tarsier2: Advancing Large Vision-Language Models from Detailed Video Description to Comprehensive Video Understanding
• video-SALMONN-o1: Reasoning-enhanced Audio-visual Large Language Model