Home Projects Sa2VA
Sa2VA
Python

Sa2VA

Official Repo For Pixel-LLM Codebase: Sa2VA (T-PAMI-26), SAMTok (CVPR-26), VRT (Arxiv-25), SaSaSa2VA (1-st solution for LSVOS)

by bytedance · GitHub
Stars
Forks
License
Created
Last commit
Language
computer-visionlarge-language-modelsmllmApache-2.0Python
View on GitHub
In plain words

Explore advanced models that enhance understanding of images and videos using AI.

You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

Claim this page →
Sa2VA — GitHub preview card
📈 Star history
1.67k1.65k
2026-07-202026-08-31
📈 Track Sa2VA

Get an email alert on its next release or when it starts trending — never miss the moment.

Free · no card · unsubscribe anytime
Get email alerts →
📄 About

Official Repo For Pixel-LLM Codebase: Sa2VA (T-PAMI-26), SAMTok (CVPR-26), VRT (Arxiv-25), SaSaSa2VA (1-st solution for LSVOS)

Sa2VA has 1.7k stars on GitHub. It has been forked 131 times. Sa2VA is written mainly in Python. It has been in active development since 2025. Sa2VA is available under the Apache-2.0 license. Its main topics are computer-vision, large-language-models, mllm.

Frequently asked questions

What is Sa2VA?

Official Repo For Pixel-LLM Codebase: Sa2VA (T-PAMI-26), SAMTok (CVPR-26), VRT (Arxiv-25), SaSaSa2VA (1-st solution for LSVOS)

Is Sa2VA open source?

Sa2VA is an open-source project. It is released under the Apache-2.0 license.

Is Sa2VA free?

Yes. Sa2VA is free and open source — you can use, modify and self-host it.

What license does Sa2VA use?

Sa2VA is available under the Apache-2.0 license.

What language is Sa2VA written in?

Sa2VA is written mainly in Python.

🏅 Maintainer of this project?
olud.ai badge — Sa2VA

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![olud.ai](https://olud.ai/badge.php?tool=bytedance-sa2va)](https://olud.ai/project/bytedance-sa2va.html)
More badge options →
🧬 Shares DNA with🧬 View the DNA map →

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.