Mitigating Visual Knowledge Forgetting in MLLM Instruction-tuning via Modality-decoupled Gradient Descent.

Junda Wu, Yuxin Xiong, Xintong Li, Yu Xia, Ruoyu Wang, Yu Wang, Tong Yu, Sungchul Kim, Ryan A. Rossi, Lina Yao, Jingbo Shang, Julian J. McAuley

Browse the full EMNLP paper archive.