# amazon-science/mm-cot

Official implementation for "Multimodal Chain-of-Thought Reasoning in Language Models" (stay tuned and more will be updated)

Repository: https://github.com/amazon-science/mm-cot
Canonical: https://ross.abutalabs.com/products/mm-cot
Homepage: https://arxiv.org/abs/2302.00923
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2024-06-12T13:50:10+00:00

## Health v2 (maintenance only)
Score: 31/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 93
- inputs: {"age_days": 1308, "days_push": 812, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3985, forks 333 (observed 2026-08-28T04:08:31.735523+00:00)

## What it is
Official PyTorch implementation of the paper 'Multimodal Chain-of-Thought Reasoning in Language Models', which adds vision features to a two-stage rationale-generation and answer-inference framework. It achieves state-of-the-art ScienceQA results with a sub-1B parameter model.

## Use cases
- reproduce multimodal chain-of-thought reasoning results
- train a model to answer science questions with images and text
- generate rationales before answering visual QA questions
- extract vision features like CLIP or ViT for ScienceQA
- experiment with two-stage CoT training frameworks
- reduce hallucination in multimodal LLM reasoning

## When to choose
- you want to reproduce or extend the Multimodal-CoT paper
- you need a two-stage rationale-then-answer pipeline for vision-language QA
- you're researching chain-of-thought reasoning with image inputs on ScienceQA or A-OKVQA

## When to avoid
- you need a production-ready multimodal inference service
- you want a general-purpose LLM framework rather than a research codebase
- you don't have GPU resources for training
- you need a maintained library with API stability guarantees

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, llm-training, nlp, image-processing
- domain: large-language-models, machine-learning, computer-vision, artificial-intelligence
- platform: python
- tags: chain-of-thought, multimodal, vision-language, research-code, scienceqa, rationale-generation, paper-implementation, research, gpu, linux

## Member repositories
- amazon-science/mm-cot (main) score 31

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:31.735523+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:24:14.666373+00:00, confidence not recorded.
  - readme: https://github.com/amazon-science/mm-cot (fetched 2026-08-28T04:08:31.735523+00:00, sha 0176136f09e5)
  - homepage: https://arxiv.org/abs/2302.00923 (fetched 2026-08-29T09:17:32.864466+00:00, sha f7ca68ee0422)
  - site_page: https://info.arxiv.org/about/donate.html (fetched 2026-08-29T09:17:32.873375+00:00, sha cca9c3a11c56)
  - site_page: https://info.arxiv.org/about/ourmembers.html (fetched 2026-08-29T09:17:32.876698+00:00, sha 47cbc55ff1de)
  - site_page: https://info.arxiv.org/about (fetched 2026-08-29T09:17:32.878812+00:00, sha a1f16f915a9a)
  - site_page: https://info.arxiv.org/labs/index.html (fetched 2026-08-29T09:17:32.875098+00:00, sha b14a8d05a0ec)
- Data as of 2026-08-30T08:39:29.467469+00:00.