@inproceedings{you-etal-2026-latent,
    title = "Latent-Condensed Transformer for Efficient Long Context Modeling",
    author = "You, Zeng  and
      Chen, Yaofo  and
      Chen, Qiuwu  and
      Sun, Ying  and
      Zhang, Shuhai  and
      Li, Yingjian  and
      Wang, Yaowei  and
      Tan, Mingkui",
    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.1176/",
    pages = "25656--25671",
    ISBN = "979-8-89176-390-6",
    abstract = "Large language models (LLMs) face significant challenges in processing long contexts due to the linear growth of the key-value (KV) cache and quadratic complexity of self-attention. Existing approaches address these bottlenecks separately: Multi-head Latent Attention (MLA) reduces the KV cache by projecting tokens into a low-dimensional latent space, while sparse attention reduces computation. However, sparse methods cannot operate natively on MLA{'}s compressed latent structure, missing opportunities for joint optimization. In this paper, we propose Latent-Condensed Attention (LCA), which directly condenses context within MLA{'}s latent space, where the representation is disentangled into semantic latent vectors and positional keys. LCA separately aggregates semantic vectors via query-aware pooling and preserves positional keys via anchor selection. This approach jointly reduces both computational cost and KV cache without adding parameters. Beyond MLA, LCA{'}s design is architecture-agnostic and readily extends to other attention mechanisms such as GQA. Theoretically, we prove a length-independent error bound. Experiments show LCA achieves up to **2.5{\texttimes}** prefilling speedup and **90{\%}** KV cache reduction at 128K context while maintaining competitive performance."
}