# gokayfem/awesome-vlm-architectures

Curated visual catalog of 155+ vision-language model (VLM/MLLM) architectures: papers, diagrams, training recipes, datasets, and a release timeline for multimodal AI agents.

Repository: https://github.com/gokayfem/awesome-vlm-architectures
Canonical: https://ross.abutalabs.com/products/awesome-vlm-architectures
Language: Markdown
License: CC0-1.0
License Family: permissive
Topics: ai-agents, architecture-diagrams, arxiv, computer-vision, deep-learning, foundation-models, large-multimodal-models, mllm, model-architecture, multimodal-ai, multimodal-llm, natural-language-processing, release-timeline, research-papers, transformers, vision-language-models, awesome, awesome-list, multimodal, vlm
Last push: 2026-07-31T21:58:54+00:00

## Health v2 (maintenance only)
Score: 68/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 95, release rhythm 35, longevity 66
- inputs: {"age_days": 930, "days_push": 33, "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 1306, forks 55 (observed 2026-08-28T04:04:18.816630+00:00)

## What it is
A curated, citation-first visual catalog of 155+ vision-language model (VLM/MLLM) architectures, linking to primary papers and summarizing architecture, training recipes, datasets, and design choices. It includes a verified release timeline and covers families from CLIP and Flamingo to current multimodal reasoning and agentic models.

## Use cases
- compare vision-language model architectures across families
- find papers on multimodal LLM design choices
- trace the evolution of VLM architectures over time
- research training recipes and datasets for multimodal models
- gather grounded references for AI agent workflows
- learn how CLIP, Flamingo, and modern VLMs differ architecturally
- find architecture diagrams for multimodal models

## When to choose
- you need a curated index of VLM/MLLM papers with architecture summaries
- you are surveying multimodal model design patterns for research or writing
- you want a chronological timeline of vision-language model releases
- you need starting references for building or studying multimodal AI agents

## When to avoid
- you need runnable code or model implementations rather than a literature catalog
- you need up-to-the-minute coverage of brand-new model releases
- you need a substitute for reading the original papers, since this is a guide to the literature

## Facets
- artifact type: learning-resource
- maturity: active
- function: documentation, developer-tools
- domain: artificial-intelligence, deep-learning, computer-vision, machine-learning, awesome-lists, tutorials
- platform: -
- tags: awesome-list, vision-language-models, vlm, mllm, multimodal, model-architectures, research-papers, curated-catalog, release-timeline, ai-agents, natural-language-processing, web-server

## Member repositories
- gokayfem/awesome-vlm-architectures (main) score 68

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:18.816630+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 2026-08-30T04:50:57.722586+00:00, confidence not recorded.
  - readme: https://github.com/gokayfem/awesome-vlm-architectures (fetched 2026-08-28T04:04:18.816630+00:00, sha 652063f3be0f)
- Data as of 2026-08-30T08:39:29.467469+00:00.