@inproceedings{zhang-etal-2026-chain,
    title = "Chain-of-Thought Compression Should Not Be Blind: {V}-Skip for Efficient Multimodal Reasoning via Dual-Path Anchoring",
    author = "Zhang, Dongxu  and
      Sun, Yiding  and
      Tan, Cheng  and
      Yan, Wenbiao  and
      Yang, Ning  and
      Zhu, Jihua  and
      Zhang, Haijun",
    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.887/",
    pages = "19402--19415",
    ISBN = "979-8-89176-390-6",
    abstract = "While Chain-of-Thought (CoT) reasoning significantly enhances the performance of Multimodal Large Language Models (MLLMs), its autoregressive nature incurs prohibitive latency constraints. Current efforts to mitigate this via token compression often fail by blindly applying text-centric metrics to multimodal contexts. We identify a critical failure mode termed Visual Amnesia, where linguistically redundant tokens are erroneously pruned, leading to hallucinations. To address this, we introduce V-Skip that reformulates token pruning as a Visual-Anchored Information Bottleneck (VA-IB) optimization problem. V-Skip employs a dual-path gating mechanism that weighs token importance through both linguistic surprisal and cross-modal attention flow, effectively rescuing visually salient anchors. Extensive experiments on Qwen2-VL and Llama-3.2 families demonstrate that V-Skip achieves a speedup with negligible accuracy loss. Specifically, it preserves fine-grained visual details, outperforming other baselines over 30{\%} on the DocVQA."
}