gokayfem/awesome-vlm-architectures resource

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1306 stars · 55 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

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

learning-resource · maturity active

documentation developer-tools artificial-intelligence deep-learning computer-vision machine-learning awesome-lists tutorials 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

For agents

markdown · JSON · MCP: product_card(name="gokayfem/awesome-vlm-architectures")