NeuPAT：面向语言保持多模态大模型的神经元感知可塑性分配调优

AI 摘要

NeuPAT提出了一种神经元感知的可塑性分配调优框架，用于在多模态指令调优过程中保留大语言模型的语言能力。该方法通过小规模探测阶段估计神经元适应模式，选择性保护语言敏感神经元，同时促进多模态适应。实验表明，NeuPAT在11个语言基准上恢复了94.5%的语言能力退化，同时保持了相当的多模态性能。

正文节选

NeuPAT: Neuron-aware Plasticity Allocation Tuning for Language-Preserving MLLMs Abstract NeuPAT selectively constrains updates to language-sensitive neurons during multimodal tuning to preserve LLM language capabilities while enabling perceptual adaptation. Multimodal expansion of large language models (LLMs) enables new perceptual capabilities but often compromises the language intelligence acquired during pretraining. In this work, we investigate this phenomenon from the perspective of interna

发布时间：—

抓取时间：2026-08-13 12:01

来源机构：Hugging Face