@inproceedings{li-etal-2026-regate,
    title = "{R}e{GATE}: Learning Faster and Better with Fewer Tokens in {MLLM}s",
    author = "Li, Chaoyu  and
      Kulkarni, Yogesh  and
      Fazli, Pooyan",
    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.2154/",
    pages = "46430--46446",
    ISBN = "979-8-89176-390-6",
    abstract = "The computational cost of training multimodal large language models (MLLMs) grows rapidly with the number of processed tokens. Existing efficiency methods mainly target inference via token reduction or merging, offering limited benefits during training. We introduce ReGATE (**Re**ference-**G**uided **A**daptive **T**oken **E**lision), an adaptive token pruning method for accelerating MLLM training. ReGATE adopts a teacher-student framework, in which a frozen teacher LLM provides per-token guidance losses that are fused with an exponential moving average of the student{'}s difficulty estimates. This adaptive scoring mechanism dynamically selects informative tokens while skipping redundant ones in the forward pass, substantially reducing computation without altering the model architecture. Across three representative MLLMs, ReGATE matches the peak accuracy of standard training on MVBench up to **2 $\times$ faster**, using only **38{\%}** of the tokens. With extended training, it even surpasses the baseline across multiple multimodal benchmarks, cutting total token usage by over **41{\%}**. Code and models will be released publicly."
}