1
Correct When Paired, Wrong When Split: Decoupling and Editing Modality-Specific Neurons in MLLMs
多模态大语言模型在配对时表现准确、拆分时出错，研究通过解耦编辑特定模态神经元来修复这一现象。
arXiv:2606.17057v1 Announce Type: cross Abstract: Although Knowledge Editing provides an efficient mechanism for updating the knowledge of Multimodal …