@inproceedings{fan-etal-2026-emcompress,
    title = "{EMC}ompress: Video-{LLM}s with Endomorphic Multimodal Compression",
    author = "Fan, Zheyu  and
      Liu, Jiateng  and
      Zhang, Yuji  and
      Wang, Zihan  and
      Fung, Yi R.  and
      Li, Manling  and
      Ji, Heng",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.8/",
    pages = "137--162",
    ISBN = "979-8-89176-395-1",
    abstract = "Video-LLMs face a fundamental tension in long-video reasoning: static, sparse frame sampling either dilutes evidence across task-irrelevant segments at significant cost or misses fine-grained temporal semantics altogether. We propose a novel, cognitively-inspired task {---} Endomorphic Multimodal Compression (EMC) {---} as a structurally-constrained sufficient-statistic problem for VideoQA, and formulate it as an endomorphic transformation F{\_}EMC : (V, Q) {\textrightarrow} (v, q) that compresses the multimodal input while preserving answer invariance across reasonable downstream models. The endomorphic form keeps the compressed output in the downstream pipeline{'}s native task space {---} a structural mirror of the filter-then-reason mechanism in the cognitive literature motivating EMC {---} distinguishing it from latent-code compression (IB / VIB) and making the formulation extensible to other multimodal settings. Under the Markov chain A {\textrightarrow} (V, Q) {\textrightarrow} (v, q), EMC realizes the classical sufficiency condition I((v, q); A) = I((V, Q); A) in its VideoQA-natural form. As a modular front-end, EMC plugs into both Video Instruction Tuning and Video Question Answering pipelines. We release the first dedicated benchmark and propose ReSimplifyIt, an EMC baseline surpassing prior methods by 0.40 F-1 with competitive query rewriting. Integrating EMC yields relative gains of 7.33{\%} in training and 33.7{\%} in inference for video-language understanding."
}