@inproceedings{zhao-etal-2026-bwla,
    title = "{BWLA}: Breaking the Barrier of {W}1{AX} Post-Training Quantization for {LLM}s",
    author = "Zhao, Zhixiong  and
      Xu, Zukang  and
      Yang, Dawei",
    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.880/",
    pages = "19264--19290",
    ISBN = "979-8-89176-390-6",
    abstract = "Large language models (LLMs) have driven major progress in NLP, yet their substantial memory and compute demands still hinder practical deployment. Binarization can compress weights to 1 bit, fundamentally lowering compute and bandwidth cost. However, existing methods cannot address activation heavy tails and thus must keep activations in high precision, preventing true end-to-end acceleration. To overcome this limitation, we propose BWLA, the first post-training quantization framework that preserves high accuracy while achieving 1-bit weight quantization together with low-bit activations (e.g., 6 bits). The Orthogonal-Kronecker Transformation (OKT) learns an orthogonal mapping via EM minimization, converting unimodal weights into symmetric bimodal forms while suppressing activation tails and incoherence. The Proximal SVD Projection (PSP) then performs lightweight low-rank refinement through proximal SVD projection, further enhancing quantizability with minimal overhead. On Qwen3-32B, BWLA reaches a Wikitext2 perplexity of 11.92 under 6-bit activations (vs. 38 from SOTA), improves five zero-shot tasks by more than 70{\%}, and delivers 3.26{\texttimes} inference speedup, demonstrating strong potential for real-world LLM compression and acceleration. The code will be available at [BWLA](https://github.com/Kishon-zzx/BWLA)."
}