M2IV: Towards Efficient and Fine-grained Multimodal In-Context Learning in Large Vision-Language Models

Abstract: Multimodal in-context learning (ICL) is a vital capability for Large Vision-LLMs (LVLMs), allowing task adaptation via contextual prompts without parameter retraining. However, its application is hindered by the token-intensive nature of inputs and the high complexity of cross-modal few-shot learning, which limits the expressive power of representation methods. To tackle these challenges, we propose \textbf{M2IV}, a method that substitutes explicit demonstrations with learnable \textbf{I}n-context \textbf{V}ectors directly integrated into LVLMs. By exploiting the complementary strengths of multi-head attention (\textbf{M}HA) and multi-layer perceptrons (\textbf{M}LP), M2IV achieves robust cross-modal fidelity and fine-grained semantic distillation through training. This significantly enhances performance across diverse LVLMs and tasks and scales efficiently to many-shot scenarios, bypassing the context window limitations. We also introduce \textbf{VLibrary}, a repository for storing and retrieving M2IV, enabling flexible LVLM steering for tasks like cross-modal alignment, customized generation and safety improvement. Experiments across seven benchmarks and three LVLMs show that M2IV surpasses Vanilla ICL and prior representation engineering approaches, with an average accuracy gain of \textbf{3.74\%} over ICL with the same shot count, alongside substantial efficiency advantages.