MMA: Multi-Modal Adapter for Vision-Language Models

Lingxiao Yang, Ru-Yuan Zhang, Yanchen Wang, Xiaohua Xie
2/9/2026

No official code found. Best implementation: ZjjConan/VLM-MultiModalAdapter (98 stars, MIT, last commit 2025-04-24).

DOISemantic Scholar

Code Implementations(1)

ZjjConan/VLM-MultiModalAdapterCommunity65%
MIT

The official pytorch implemention of our CVPR-2024 paper "MMA: Multi-Modal Adapter for Vision-Language Models".

987Shell, PythonMar 9, 20241 years agoMIT

Cite this paper

@article{yang2026mma,
  title  = {MMA: Multi-Modal Adapter for Vision-Language Models},
  author = {Lingxiao Yang and Ru-Yuan Zhang and Yanchen Wang and Xiaohua Xie},
  year   = {2026},
  doi    = {10.1109/CVPR52733.2024.02249},
  url    = {https://doi.org/10.1109/CVPR52733.2024.02249},
  journal = {CVPR 2024 2024}
}

Discussion