@inproceedings{hu-etal-2026-tinyalign,
    title = "{T}iny{A}lign: Boosting Lightweight Vision-Language Models by Mitigating Modal Alignment Bottlenecks",
    author = "Hu, Yuanze  and
      Wang, Xinyu  and
      Yang, Zhichao  and
      Li, Gen  and
      Qiu, Ye  and
      Fan, Zhaoxin  and
      Sun, Yifan  and
      wu, Wenjun  and
      Dong, Jin  and
      Deng, Xiaotie",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.223/",
    pages = "4585--4597",
    ISBN = "979-8-89176-395-1",
    abstract = "Lightweight Vision-Language Models (VLMs) are indispensable for resource-constrained applications. The prevailing approach to aligning vision and language models involves freezing both the vision encoder and the language model while training small connector modules. However, this strategy heavily depends on the intrinsic capabilities of the language model, which can be suboptimal for lightweight models with limited representational capacity. In this work, we investigate this alignment bottleneck through the lens of mutual information, positing that the constrained capacity of the language model inherently limits the Effective Mutual Information (EMI) between multimodal inputs and outputs, thereby compromising alignment quality. To address this challenge, we propose TinyAlign, a novel framework inspired by Retrieval-Augmented Generation, which strategically retrieves relevant context from a memory bank constructed from training data to enrich multimodal inputs and enhance their alignment. Extensive empirical evaluations reveal that TinyAlign significantly reduces training loss, accelerates convergence, and enhances task performance with negligible computational overhead. Remarkably, it allows models to achieve baseline-level performance with only 40{\%} of the fine-tuning data, highlighting exceptional data efficiency. Our work thus offers a practical pathway for developing more capable lightweight VLMs while introducing a fresh theoretical lens to better understand and address alignment bottlenecks in constrained multimodal systems."
}