Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey
| Date | Stars |
|---|---|
| 2026-07-24 | 1017 |
| 2026-07-25 | 1017 |
| 2026-07-28 | 1017 |
| 2026-07-30 | 1017 |
| 2026-08-06 | 1017 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<h2 align="center">Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey</h2> <!-- <h1 align="center">Awesome-MCoT</h1> --> <div align="center"> [](https://arxiv.org/abs/2503.12605) [](https://github.com/yaotingwangofficial/Awesome-MCoT/issues/1) [](https://github.com/yaotingwangofficial/Awesome-MCoT/discussions) [](https://github.com/yaotingwangofficial/Awesome-MCoT/issues/4) [](https://join.slack.com/t/mcot/shared_invite/zt-329e3dpuf-Fr~umfXWlhxONrdgERKSaQ) </div> > 💡 *You're very welcome to join our discussion (on WeChat or Slack) on the topic of multimodal reasoning.* > 📌 *Please feel free to ping us for any possibly missed related work — see [CONTRIBUTING.md](CONTRIBUTING.md) for how to suggest a paper.* <p align="center"> <img src="assets/cover-teasure-map.png" width="85%" alt="MCoT cover figure"> </p> # 🎇 Introduction Multimodal chain-of-thought (MCoT) reasoning has garnered attention for its ability to enhance ***step-by-step*** reasoning in multimodal contexts, particularly within multimodal large language models (MLLMs). Current MCoT research explores various methodologies to address the challenges posed by images, videos, speech, audio, 3D data, and structured data, achieving success in fields such as robotics, healthcare, and autonomous driving. However, despite these advancements, the field lacks a comprehensive review that addresses the numerous remaining challenges. To fill this gap, we present [**_the first systematic survey of MCoT reasoning_**](https://arxiv.org/abs/2503.12605), elucidating the foundational concepts and definitions pertinent to this area. Our work includes a detailed taxonomy and an analysis of existing methodologies across different applications, as well as insights into current challenges and future research directions aimed at fostering the development of multimodal reasoning. <p align="center"> <img src="assets/mcot_timeline-1.png" width="90%" alt="MCoT research timeline"> </p> --- ### Updates > 2025-05-20: We upload the Chinese language version, enjoy! <br> > 2025-04-25: We gain 500 stars! Thank you all! <br> > 2025-03-18: We release the Awesome-MCoT repo and survey. --- # 📕 Table of Contents - [🎖 MCoT Datasets and Benchmarks](#-mcot-datasets-and-benchmarks) - [Training with rationale](#tab-1-datasets-for-mcot-training-with-rationale) - [Evaluation without rationale](#tab-2-benchmarks-for-mcot-evaluation-without-rationale) - [Evaluation with rationale](#tab-3-benchmarks-for-mcot-evaluation-with-rationale) - [🎊 Multimodal Reasoning via RL](#-multimodal-reasoning-via-rl) - [✨ MCoT Over Various Modalities](#-mcot-over-various-modalities) - [MCoT Reasoning Over Image](#mcot-reasoning-over-image) - [MCoT Reasoning Over Video](#mcot-reasoning-over-video) - [MCoT Reasoning Over 3D](#mcot-reasoning-over-3d) - [MCoT Reasoning Over Audio and Speech](#mcot-reasoning-over-audio-and-speech) - [MCoT Reasoning Over Table and Chart](#mcot-reasoning-over-table-and-chart) - [Cross-modal CoT Reasoning](#cross-modal-cot-reasoning) - [🔥 MCoT Methodologies](#-mcot-methodologies) - [Rationale Construction](#rationale-construction) - [Structural Reasoning](#structural-reasoning) - [Information Enhancing](#information-enhancing) - [Objective Granularity](#objective-granularity) - [Multimodal Rationale](#multimodal-rationale) - [Test-Time Scaling](#test-time-scaling) - [🎨 Applications with MCoT Reasoning](#-applications-with-mcot-reasoning) - [Embodie
Excerpt of 82,966 characters
Read on GitHub
61
13
Hao Fei · University of Oxford · United Kingdom
2
Xiongkun Linghu · Beijing Academy of Artificial Intelligence · China
2
Ikko Eltociear Ashimine · Japan
1
Wenqi Zhang · Zhejiang University · China
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:1d7d3acd5fa2acdc, topic:multimodal, desc:multimodal, readme:multimodal
matched fp:1d7d3acd5fa2acdc, topic:instruction-tuning