# zhaochen0110/Awesome_Think_With_Images

Resources and paper list for "Thinking with Images for LVLMs". This repository accompanies our survey on how LVLMs can leverage visual information for complex reasoning, planning, and generation.

Repository: https://github.com/zhaochen0110/Awesome_Think_With_Images
Canonical: https://ross.abutalabs.com/products/awesome_think_with_images
Homepage: https://arxiv.org/pdf/2506.23918
License Family: other
Topics: large-vision-language-models, multimodal-reasoning-visual-reasoning, survey-awesome-list, thinking-with-images
Last push: 2026-03-09T13:42:12+00:00

## Health v2 (maintenance only)
Score: 51/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 71, release rhythm 35, longevity 32
- inputs: {"age_days": 460, "days_push": 177, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1503, forks 47 (observed 2026-08-28T04:04:54.569655+00:00)

## What it is
A curated awesome-list repository accompanying a survey paper on 'Thinking with Images' for large vision-language models (LVLMs). It organizes research into three stages of cognitive autonomy: tool-driven visual exploration, programmatic visual manipulation, and intrinsic visual imagination.

## Use cases
- find papers on multimodal reasoning with images
- research how LVLMs use visual tools for reasoning
- survey visual reasoning methods for vision-language models
- get started with thinking-with-images research
- find resources on programmatic visual manipulation
- track state-of-the-art in intrinsic visual imagination
- prepare a literature review on multimodal AI reasoning

## When to choose
- you need a comprehensive, structured paper list on visual reasoning in LVLMs
- you are starting research on multimodal reasoning and want curated foundations
- you want to follow the three-stage taxonomy of tool use, visual programming, and visual imagination

## When to avoid
- you need runnable code or a software library rather than a paper list
- you want a general multimodal AI resource not focused on visual reasoning
- you need production tooling for vision-language model deployment

## Facets
- artifact type: learning-resource
- maturity: active
- function: nlp, computer-vision, machine-learning
- domain: artificial-intelligence, computer-vision, awesome-lists, tutorials
- platform: -
- tags: awesome-list, survey-paper, multimodal-reasoning, vision-language-models, research-curation, thinking-with-images, natural-language-processing, web-server

## Member repositories
- zhaochen0110/Awesome_Think_With_Images (main) score 51

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:54.569655+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 2026-08-30T04:32:51.075231+00:00, confidence not recorded.
  - readme: https://github.com/zhaochen0110/Awesome_Think_With_Images (fetched 2026-08-28T04:04:54.569655+00:00, sha 3ac7e49a7979)
- Data as of 2026-08-30T08:39:29.467469+00:00.