@inproceedings{gu-etal-2026-btc,
    title = "{BTC}-{LLM}: Efficient Sub-1-Bit {LLM} Quantization via Learnable Transformation and Binary Codebook",
    author = "Gu, Hao  and
      Li, Lujun  and
      Wang, Hao  and
      Wang, Lei  and
      Wang, Zheyu  and
      Liu, Bei  and
      Liu, Jiacheng  and
      Zhu, Qiyuan  and
      Han, Sirui  and
      Guo, Yike",
    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.1066/",
    pages = "23274--23294",
    ISBN = "979-8-89176-390-6",
    abstract = "Binary quantization represents the most extreme form of compression, reducing weights to $\pm$1 for maximal memory and computational efficiency. While recent sparsity-aware binarization achieves sub-1-bit compression via weight pruning, it faces critical challenger: performance degradation, mask-management overhead, and limited hardware compatibility. In this paper, we present BTC-LLM, a novel sub-1-bit LLM quantization framework that leverages binary pattern clustering and weight transformation to overcome these limitations. Our approach incorporates two key innovations: (1) a Binary Codebook that clusters recurring vectors into compact indices using custom distance metrics and sign-based updates; (2) a Learnable Transformation that reduces outliers and promotes shared sign patterns among binary weights. This eliminates sparse masks, enabling efficient inference on standard hardware. Extensive evaluations across LLaMA, Qwen, and FBI-LLM families demonstrate that BTC-LLM achieves state-of-the-art results in extreme compression (1.11{--}0.7 bits). Notably, BTC-LLM compressed to 0.8 bits on LLaMA-2-13B maintains high performance{---}with only a 3.1{\%} accuracy drop in zero-shot benchmarks{---}while delivering a 1.6$\times$ speedup over FP16."
}