@inproceedings{li-etal-2026-jw,
    title = "{JW}-{SVD}: Bridging the Cross-Modal Mismatch in Post-Training {MLLM} Compression",
    author = "Li, Runchao  and
      Fu, Yao  and
      Sheng, Mu  and
      Yu, Haotian  and
      Long, Xianxuan  and
      Loparo, Kenneth A.",
    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.1977/",
    pages = "42691--42702",
    ISBN = "979-8-89176-390-6",
    abstract = "Post-training compression of Multimodal LLMs faces a fundamental geometric conflict: parameter subspaces optimized for text often suppress orthogonal visual features. We demonstrate that standard SVD fails to resolve this cross-modal mismatch, causing catastrophic visual degradation. To bridge this gap, we introduce Joint-Whitening SVD (JW-SVD), a dual-objective framework that aligns vision and language manifolds via a Joint Covariance basis, preserving features critical to both. Additionally, we propose Global Spectrum-Aware Truncation to dynamically transfer parameter budget from the redundant Vision Tower to the sensitive Backbone. Experiments on Qwen2.5-VL and Llama-3-Next confirm that JW-SVD demonstrates superior retention of both text and image capabilities. In addition, it resolves the modality trade-off: it recovers over 30{\%} of perceptual performance lost by baselines while maintaining parity in textual reasoning, enabling robust multimodal performance even at extreme compression rates."
}