
Sa2VA
by bytedance (organization)
Official Repo For Pixel-LLM Codebase: Sa2VA (T-PAMI-26), SAMTok (CVPR-26), VRT (Arxiv-25), SaSaSa2VA (1-st solution for LSVOS) (description from the project’s GitHub page)
Repository facts
- Stars
- 1,688
- Forks
- 133
- Open issues and pull requests
- 27
- Primary language
- Python
- License
- Apache License 2.0 (Apache-2.0)
- Owner
- bytedance · Organization
- Created
- Jan 6, 2025
- Last push
- Sep 8, 2026
Topics
Related projects
Projects that share this one’s GitHub topics.
Rank 3,635: cambrian-mllm/cambrian
Cambrian-1 is a family of multimodal LLMs with a vision-centric design.
2,011 starsPythonApache-2.0Last push Nov 7, 2025
Rank 6,884: taco-group/4KAgent
[NeurIPS 2025] 4KAgent: Agentic Any Image to 4K Super-Resolution. An intelligent computer vision agent that can magically restore any image to perfect-4K!
833 starsPythonApache-2.0Last push Sep 24, 2025
Rank 2,125: NVlabs/Eagle
Eagle: Frontier Vision-Language Models with Data-Centric Strategies
3,707 starsPythonApache-2.0Last push Jun 24, 2026
Rank 2,158: NExT-GPT/NExT-GPT
Code and models for ICML 2024 paper, NExT-GPT: Any-to-Any Multimodal Large Language Model
3,635 starsPythonBSD-3-ClauseLast push May 13, 2025
Rank 6,522: EvolvingLMMs-Lab/NEO
NEO Series: Native Vision-Language Models from First Principles
902 starsPythonApache-2.0Last push Jul 27, 2026
Rank 6,666: LYL1015/JarvisArt
[NeurIPS' 2025] JarvisArt: Liberating Human Artistic Creativity via an Intelligent Photo Retouching Agent
874 starsPythonOther licenseLast push Apr 4, 2026