Awesome Multimodal AI Papers

A curated and continuously updated collection of scholarly research on multimodal & vision-language models, structured to support systematic exploration and academic inquiry.

Browse Papers Get the Daily Digest

Updated daily.

Explore the collection

📜
All Papers
Every paper — sortable by year, citations, stars, likes.
🔥
Trending
What the community is talking about right now.
🏷️
Tags
Browse by topic. Fast filter across the collection.
🤖
Ask AI
Ask anything in plain English — answers cite real papers.
🧪
Tools & Code
GitHub repos sorted by stars and recent activity.
👥
Authors
Who's publishing what — sorted by output and citations.
More tools
🗺️
2D Map
t-SNE embedding of every paper. Zoom, pan, click.
🧭
Topic Explorer
Discovered themes and top papers per topic.
📚
Reading Packs
Curated journeys through canonical and frontier papers.
📊
Leaderboards
Benchmark SOTA — who's leading each task.
📝
Blogs & Books
High-signal blog posts and books on the field.
🎓
Learn
Structured roadmap through the research.

Awesome Multimodal AI Papers
Key research topics in Multimodal & Vision-Language Models

A personal research project — provided as-is, no warranties.