@inproceedings{zong-etal-2026-l2dir,
    title = "{L}2{D}ir: Integrating $L\_2$-Norm and Directional Alignment for Unsupervised Contrastive Representation Learning in Multimodal Retrieval",
    author = "Zong, Tianyu  and
      Dai, Rui  and
      Yi, Hongzhu  and
      Wang, Yuanxiang  and
      Zhang, Zhenghao  and
      Guan, Zhenyu  and
      Yang, Yujia  and
      Shi, Bingkang  and
      Ding, Yueyang  and
      Chu, Xiangxiang  and
      Liu, Kaikui  and
      Xu, Jungang",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.1604/",
    pages = "34717--34740",
    ISBN = "979-8-89176-390-6",
    abstract = "Multimodal representation learning primarily relies on contrastive objectives such as InfoNCE to align diverse modalities. However, these methods focus almost exclusively on directional alignment and often neglect the intrinsic role of embedding magnitudes (L2-norm) in the contrastive process. To bridge this gap, we propose L2Dir, a plug-and-play framework designed to optimize L2-norm alignment and Directional consistency jointly. As a highly efficient solution, L2Dir doesn{'}t require extra data, distillation, or external supervision. It can be integrated seamlessly into existing pipelines by employing a lightweight MLP to reconstruct magnitudes from frozen backbone features. Extensive evaluations across 95 tasks using UniIR and VLM2Vec-V2 frameworks demonstrate that L2Dir yields consistent and significant performance gains over established baselines across various backbones and scales, proving that explicit magnitude modeling is a versatile and potent strategy for refining unsupervised multimodal representations. The source code for L2Dir in VLM2Vec-V2 is available in the supplementary materials."
}