@inproceedings{liu-etal-2026-dream,
    title = "{DREAM}-{S}: Speculative Decoding with Searchable Drafting and Target-Aware Refinement for Multimodal Generation",
    author = "Liu, Zining  and
      Hu, Yunhai  and
      Xia, Tianhua  and
      Bao, BO  and
      Sather, Eric  and
      Thangarasa, Vithursan  and
      Zhang, Sai Qian",
    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.2177/",
    pages = "47031--47045",
    ISBN = "979-8-89176-390-6",
    abstract = "Speculative decoding (SD) has proven to be an effective technique for accelerating autoregressive generation in large language models (LLMs), however its application to vision-language models (VLMs) remains relatively unexplored. We propose DREAM-S, a novel SD framework designed specifically for fast and efficient decoding in VLMs. DREAM-S leverages a neural architecture search (NAS) framework with target-aware supernet training to automatically identify both the optimal interaction strategy between the draft and target models, and the most suitable draft model architecture for the underlying hardware implementation platform. DREAM-S additionally incorporates adaptive intermediate feature distillation, guided by attention entropy, to enable efficient draft training. Experiments on a range of well-established VLMs show that DREAM-S achieves up to a 3.85$\times$ speedup compared to standard decoding approaches and significantly outperforms existing SD baselines."
}