ATH-MaaS/Awesome-Unified-Multimodal-Models resource

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

1312 stars · 46 forks observed · 2026-08-28

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

A curated awesome-list repository accompanying a survey paper on unified multimodal models that handle both image-text understanding and generation. It catalogs diffusion-based, autoregressive, and hybrid architectures, plus benchmarks and datasets for multimodal tasks.

Use cases

• find papers on unified multimodal understanding and generation models
• compare diffusion vs autoregressive multimodal architectures
• find benchmarks for evaluating text-to-image generation
• find datasets for multimodal understanding and image editing
• research any-to-any multimodal models
• get an overview of the unified multimodal model landscape

When to choose

• you are researching unified multimodal models and need a categorized paper collection
• you need benchmarks or datasets for multimodal understanding or generation tasks
• you want a timeline and taxonomy of the field from a survey paper

When to avoid

• you need runnable code or a model implementation rather than a resource list
• you need a production tool for multimodal inference
• you are looking for audio- or video-only models rather than image-text unified models

Facets

learning-resource · maturity active

machine-learning data-science documentation artificial-intelligence machine-learning deep-learning computer-vision awesome-lists tutorials awesome-list multimodal-models survey text-to-image vision-language-models diffusion benchmarks research natural-language-processing web-server

Member repositories

For agents

markdown · JSON · MCP: product_card(name="ATH-MaaS/Awesome-Unified-Multimodal-Models")