这篇论文发现多模态模型持续微调时，投影仪会比主干更容易遗忘旧知识，并提出了PMA框架来解决，在两个基准上效果超过现有方法，值得做持续学习的读者看看。
多模态大语言模型（MLLM）依赖投影仪对齐视觉表示与语言嵌入空间。在持续指令微调中，视觉分布变化和指令语义演化导致投影仪漂移，引发投影仪级别遗忘——现有方法主要关注LLM骨干而忽视该问题。本文提出PMA框架，通过轻量级表示描述符检测多模态分布偏移，按需渐进扩展投影仪专家，并保留原始预训练投影仪作为稳定锚点。在两个MCIT基准（如MMBench持续版本）上，PMA结合现有方法一致超越先前最优结果，且在不同MLLM骨干上表现鲁棒。
Progressive Multimodal Alignment for Continual Instruction Tuning
Multimodal Large Language Models (MLLMs) rely on a projector to align visual representations with the language embedding space, making it central to cross-modal understanding. In Multimodal Continual Instruction Tuning (MCIT), however, shifting visual distributions and evolving instruction semantics cause this shared projector to drift, leading to projector-level forgetting, an issue largely overlooked by methods that focus primarily on the LLM backbone. We introduce Progressive Multimodal Alignment (PMA), a framework that enables the projector to adapt continually while preserving previously learned alignment. PMA detects multimodal distribution shifts via a lightweight representation descriptor and progressively expands projector experts only when needed. An expandable router integrates expert outputs based on multimodal features, while the original pretrained projector is retained as a stable alignment anchor. This progressive mechanism balances stability and plasticity with sub-linear parameter growth and serves as a method-agnostic add-on to existing MCIT approaches. Extensive experiments on two recent MCIT benchmarks demonstrate that mitigating projector-level forgetting yields consistent gains over prior state-of-the-art methods when combined with PMA. Moreover, PMA scales across diverse MLLM backbones, demonstrating robust and broadly applicable MCIT performance.