Recent years have witnessed remarkable advances in Large Vision-Language Models (LVLMs), which have achieved human-level performance across various complex vision-language tasks. Following LLaVA's paradigm, mainstream LVLMs typically employ a shallow MLP for visual-language alignment through a two-stage training process: pretraining for cross-modal alignment followed by instruction tuning. While this approach has proven effective, the underlying mechanisms of how MLPs bridge the modality gap remain poorly understood. Although some research has explored how LLMs process transformed visual tokens, few studies have investigated the fundamental alignment mechanism. Furthermore, the MLP adapter requires retraining whenever switching LLM backbones. To address these limitations, we first investigate the working principles of MLP adapters and discover that they learn to project visual embeddings into subspaces spanned by corresponding text embeddings progressively. Based on this insight, we propose LangBridge, a novel adapter that explicitly maps visual tokens to linear combinations of LLM vocabulary embeddings. This innovative design enables pretraining-free adapter transfer across different LLMs while maintaining performance. Our experimental results demonstrate that a LangBridge adapter pre-trained on Qwen2-0.5B can be directly applied to larger models such as LLaMA3-8B or Qwen2.5-14B while maintaining competitive performance. Overall, LangBridge enables interpretable vision-language alignment by grounding visual representations in LLM vocab embedding, while its plug-and-play design ensures efficient reuse across multiple LLMs with nearly no performance degradation. See our project page atthis https URL
View on arXiv@article{liao2025_2503.19404,
title={ LangBridge: Interpreting Image as a Combination of Language Embeddings },
author={ Jiaqi Liao and Yuwei Niu and Fanqing Meng and Hao Li and Changyao Tian and Yinuo Du and Yuwen Xiong and Dianqi Li and Xizhou Zhu and Li Yuan and Jifeng Dai and Yu Cheng },
journal={arXiv preprint arXiv:2503.19404},
year={ 2025 }
}