---
title: "BWLA — paper by Zhao et al. (2026) — summary and ideas"
description: "The authors (Houmo AI) introduce BWLA, a retraining-free post-training quantization framework for 1-bit weights combined… 34 references."
authors: ["Zhixiong Zhao", "Zukang Xu", "Dawei Yang"]
year: 2026
venue: "Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/2026.acl-long.880/"
doi: "10.18653/v1/2026.acl-long.880"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/zhao-2026-bwla-breaking-barrier-w1ax-post/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/zhao-2026-bwla-breaking-barrier-w1ax-post/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/25/) / BWLA: Breaking the Barrier of W1AX Post-Training Quantization for LLMs

# BWLA: Breaking the Barrier of W1AX Post-Training Quantization for LLMs

**Authors:** Zhixiong Zhao, Zukang Xu and Dawei Yang · **Year:** 2026 · **Venue:** [Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2026](https://md.research.elamur.ai/free/en/venues/acl/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.acl-long.880/) · [PDF](https://aclanthology.org/2026.acl-long.880.pdf) · [DOI 10.18653/v1/2026.acl-long.880](https://doi.org/10.18653/v1/2026.acl-long.880) · [OpenAlex](https://openalex.org/W7166822996)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary

Binarizing LLM weights to 1 bit greatly reduces storage and bandwidth. However, earlier binarization methods such as BiLLM and ARB-LLM keep activations in high precision, because activation outliers and heavy tails make low-bit activation quantization fail. This forces weight dequantization at inference and limits real speedups.

The authors (Houmo AI) introduce BWLA, a retraining-free post-training quantization framework for 1-bit weights combined with low-bit activations (W1AX). It has two components:

- **Orthogonal-Kronecker Transformation (OKT)** learns an orthogonal rotation, fitted with a gradient-free EM-style procedure. The rotation is built cheaply as a Kronecker product of two small orthogonal matrices. It reshapes bell-shaped per-channel weights into symmetric two-peaked distributions that suit the ±1 codebook. Because the matrix is orthogonal, applying it to activations preserves model outputs while flattening outliers.
- **Proximal SVD Projection (PSP)** adds a small truncated-SVD low-rank correction that absorbs remaining outliers.

Experiments on LLaMA and Qwen3 models show BWLA is the first pure PTQ method to stay accurate in this regime. This makes end-to-end accelerated binary LLM inference practical.

## Key points

- On Qwen3-32B with 6-bit activations, BWLA reaches a Wikitext2 perplexity of 11.92, versus about 38 for the previous best method. Its gains on five zero-shot QA tasks exceed 70%.
- On an NVIDIA RTX A6000, a W1A8 LLaMA2-13B runs at 77.31 tokens/s, compared with 23.70 for FP16 and 55.35 for W4A4 OSTQuant. This is a 3.26× speedup over FP16, and parameter memory drops from 23.7 GB to 3.94 GB.
- Making the Kronecker factors more symmetric cuts OKT overhead from roughly 1 bit to 0.01 bit, at a cost of about 3% zero-shot accuracy. A PSP rank ratio of 0.005 gives the best cost/quality balance.
- Under W1A6, BWLA achieves a WikiText2 perplexity more than 70% below BiLLM's and more than 50% below ARB-LLM's. Quantization takes only about 25 minutes longer than BiLLM on average.
- Stated limitations: accuracy degrades at W1A4, the method relies only on linear rotations, and it currently supports only integer formats (formats such as MXFP4 are not yet covered).

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

📚 Shelves (7): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 3,486 works · [⚙️ Engineering](https://md.research.elamur.ai/free/en/shelves/engineering/) · 188 works · [⚙️ Electrical and Electronic Engineering](https://md.research.elamur.ai/free/en/shelves/engineering/electrical-and-electronic-engineering/) · 33 works

🧭 Topics (2): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 3,894 works · [🪶 Efficient models & compression](https://md.research.elamur.ai/free/en/topics/efficient-models/) · 297 works

## Cite

Cite as: Zhixiong Zhao, Zukang Xu and Dawei Yang. 2026. BWLA: Breaking the Barrier of W1AX Post-Training Quantization for LLMs. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{zhao2026bwla,
  title = {{BWLA: Breaking the Barrier of W1AX Post-Training Quantization for LLMs}},
  author = {Zhixiong Zhao, Zukang Xu and Dawei Yang},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.880},
  url = {https://doi.org/10.18653/v1/2026.acl-long.880}
}
```

- [← previous Business as Rulesual: A Benchmark and Framework for Business Rule Flow Modeling with LLMs](https://md.research.elamur.ai/free/en/papers/yang-2026-business-as-rulesual-benchmark-framework/)
- [next → ByteBreaker@DravidianLangTech 2026: XLM-RoBERTa Large with Sliding-Window Chunking and Top-K Mean Pooling for Writing Style Classification](https://md.research.elamur.ai/free/en/papers/sai-2026-bytebreaker-dravidianlangtech-2026-xlm-roberta/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/25/)

## References

34 references, 15 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Saleh Ashkboos, Amirkeivan Mohtashami, Maximilian L. Croci, Bo Li, Pashmina Cameron, Martin Jaggi, Dan Alistarh, Torsten Hoefler, and James Hensman. 2024. [Quarot: Outlier-free 4-bit inference in rotated llms](https://md.research.elamur.ai/free/en/papers/ashkboos-2024-quarot-outlier-free-4-bit/). Preprint, arXiv:2404.00456.
2. Haoli Bai, Wei Zhang, Lu Hou, Lifeng Shang, Jing Jin, Xin Jiang, Qun Liu, Michael Lyu, and Irwin King. 2021. [Binarybert: Pushing the limit of bert quantization](https://md.research.elamur.ai/free/en/papers/bai-2021-binarybert-pushing-limit-bert-quantization/). Preprint, arXiv:2012.15701.
3. Yonatan Bisk, Rowan Zellers, Ronan Le Bras, Jianfeng Gao, and Yejin Choi. 2019. [Piqa: Reasoning about physical commonsense in natural language](https://md.research.elamur.ai/free/en/papers/bisk-2019-piqa-reasoning-about-physical-commonsense/). Preprint, arXiv:1911.11641.
4. Mark Chen, Jerry Tworek, Heewoo Jun, Qiming Yuan, Henrique Ponde de Oliveira Pinto, Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, Alex Ray, Raul Puri, Gretchen Krueger, Michael Petrov, Heidy Khlaaf, Girish Sastry, Pamela Mishkin, Brooke Chan, Scott Gray, and 39 others. 202… — [Evaluating Large Language Models Trained on Code](https://md.research.elamur.ai/free/en/papers/chen-2021-evaluating-large-language-models-trained/)
5. Peter Clark, Isaac Cowhey, Oren Etzioni, Tushar Khot, Ashish Sabharwal, Carissa Schoenick, and Oyvind Tafjord. 2018. [Think you have solved question answering? try arc, the ai2 reasoning challenge](https://md.research.elamur.ai/free/en/papers/clark-2018-think-have-solved-question-answering/). Preprint, arXiv:1803.05457.
6. Karl Cobbe, Vineet Kosaraju, Mohammad Bavarian, Mark Chen, Heewoo Jun, Lukasz Kaiser, Matthias Plappert, Jerry Tworek, Jacob Hilton, Reiichiro Nakano, Christopher Hesse, and John Schulman. 2021. [Training verifiers to solve math word problems](https://md.research.elamur.ai/free/en/papers/cobbe-2021-training-verifiers-solve-math-word/). Preprint, arXiv:2110.14168.
7. Arthur P Dempster, Nan M Laird, and Donald B Rubin. 1977. Maximum likelihood from incomplete data via the em algorithm. Journal of the Royal Statistical Society: Series B, 39(1):1–38. [find](https://scholar.google.com/scholar?q=Arthur+P+Dempster%2C+Nan+M+Laird%2C+and+Donald+B+Rubin%2E+1977%2E+Maximum+likelihood+from+incomplete+data+via+the+em+algorithm%2E+Journal+of+the+Royal+Statistical+Society%3A+Series+B%2C+39%281%29%3A1%E2%80%9338%2E)
8. Elias Frantar, Saleh Ashkboos, Torsten Hoefler, and Dan Alistarh. 2023. Gptq: Accurate post-training quantization for generative pre-trained transformers. Preprint, arXiv:2210.17323. [find](https://scholar.google.com/scholar?q=Elias+Frantar%2C+Saleh+Ashkboos%2C+Torsten+Hoefler%2C+and+Dan+Alistarh%2E+2023%2E+Gptq%3A+Accurate+post%2Dtraining+quantization+for+generative+pre%2Dtrained+transformers%2E+Preprint%2C+arXiv%3A2210%2E17323%2E)
9. Leo Gao, Jonathan Tow, Behnam Abbasi, Stella Biderman, Sidney Black, Anthony DiPofi, Colin Foster, Luke Golding, Jenness Hsu, Alexandre Le Noac’h, Henry Li, Kyle McDonell, Niklas Muennighoff, Charles Ociepa, Jason Phang, Laura Reynolds, Hailey Schoelkopf, Anthony Skowron, Lintang Sutawika, and 5 oth… [find](https://scholar.google.com/scholar?q=Leo+Gao%2C+Jonathan+Tow%2C+Behnam+Abbasi%2C+Stella+Biderman%2C+Sidney+Black%2C+Anthony+DiPofi%2C+Colin+Foster%2C+Luke+Golding%2C+Jenness+Hsu%2C+Alexandre+Le+Noac%E2%80%99h%2C+Henry+Li%2C+Kyle+McDonell%2C+Niklas+Muennighoff%2C+Charles+)
10. Aaron Grattafiori, Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Alex Vaughan, Amy Yang, Angela Fan, Anirudh Goyal, Anthony Hartshorn, Aobo Yang, Archi Mitra, Archie Sravankumar, Artem Korenev, Arthur Hinsvark, and 542 o… — [The Llama 3 Herd of Models](https://md.research.elamur.ai/free/en/papers/grattafiori-2024-llama-3-herd-models/)
11. Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, and Jacob Steinhardt. 2021. [Measuring massive multitask language understanding](https://md.research.elamur.ai/free/en/papers/hendrycks-2020-measuring-massive-multitask-language-understanding/). Preprint, arXiv:2009.03300.
12. Xing Hu, Yuan Cheng, Dawei Yang, Zukang Xu, Zhihang Yuan, Jiangyong Yu, Chen Xu, Zhe Jiang, and Sifan Zhou. 2025. Ostquant: Refining large language model quantization with orthogonal and scaling transformations for better distribution fitting. Preprint, arXiv:2501.13987. — [arXiv:2501.13987](https://arxiv.org/abs/2501.13987) [find](https://scholar.google.com/scholar?q=Xing+Hu%2C+Yuan+Cheng%2C+Dawei+Yang%2C+Zukang+Xu%2C+Zhihang+Yuan%2C+Jiangyong+Yu%2C+Chen+Xu%2C+Zhe+Jiang%2C+and+Sifan+Zhou%2E+2025%2E+Ostquant%3A+Refining+large+language+model+quantization+with+orthogonal+and+scaling+trans)
13. Wei Huang, Yangdong Liu, Haotong Qin, Ying Li, Shiming Zhang, Xianglong Liu, Michele Magno, and Xiaojuan Qi. 2024. Billm: Pushing the limit of post-training quantization for llms. Preprint, arXiv:2402.04291. [find](https://scholar.google.com/scholar?q=Wei+Huang%2C+Yangdong+Liu%2C+Haotong+Qin%2C+Ying+Li%2C+Shiming+Zhang%2C+Xianglong+Liu%2C+Michele+Magno%2C+and+Xiaojuan+Qi%2E+2024%2E+Billm%3A+Pushing+the+limit+of+post%2Dtraining+quantization+for+llms%2E+Preprint%2C+arXiv%3A2402)
14. David R Hunter and Kenneth Lange. 2004. A tutorial on mm algorithms. The American Statistician, 58(1):30– 37. [find](https://scholar.google.com/scholar?q=David+R+Hunter+and+Kenneth+Lange%2E+2004%2E+A+tutorial+on+mm+algorithms%2E+The+American+Statistician%2C+58%281%29%3A30%E2%80%93+37%2E)
15. Even better llm quantization with hadamard incoherence and lattice codebooks. Preprint, arXiv:2402.04396. Zhiteng Li, Xianglong Yan, Tianao Zhang, Haotong Qin, Dong Xie, Jiang Tian, zhongchao shi, Linghe Kong, Yulun Zhang, and Xiaokang Yang. 2024. Arb-llm: Alternating refined binarizations for large… — [QuIP#: Even Better LLM Quantization with Hadamard Incoherence and Lattice Codebooks](https://md.research.elamur.ai/free/en/papers/tseng-2024-quip-even-better-llm-quantization/)
16. Hongyu Wang, Shuming Ma, and Furu Wei. 2024. Bitnet a4.8: 4-bit activations for 1-bit llms. Preprint, arXiv:2411.04965. — [arXiv:2411.04965](https://arxiv.org/abs/2411.04965) [find](https://scholar.google.com/scholar?q=Hongyu+Wang%2C+Shuming+Ma%2C+and+Furu+Wei%2E+2024%2E+Bitnet+a4%2E8%3A+4%2Dbit+activations+for+1%2Dbit+llms%2E+Preprint%2C+arXiv%3A2411%2E04965%2E+%E2%80%94+%5BarXiv%3A2411%2E04965%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2411%2E04965%29)
17. Ji Lin, Jiaming Tang, Haotian Tang, Shang Yang, Wei-Ming Chen, Wei-Chen Wang, Guangxuan Xiao, Xingyu Dang, Chuang Gan, and Song Han. 2024. Awq: Activation-aware weight quantization for llm compression and acceleration. Preprint, arXiv:2306.00978. [find](https://scholar.google.com/scholar?q=Ji+Lin%2C+Jiaming+Tang%2C+Haotian+Tang%2C+Shang+Yang%2C+Wei%2DMing+Chen%2C+Wei%2DChen+Wang%2C+Guangxuan+Xiao%2C+Xingyu+Dang%2C+Chuang+Gan%2C+and+Song+Han%2E+2024%2E+Awq%3A+Activation%2Daware+weight+quantization+for+llm+compression)
18. Zechun Liu, Changsheng Zhao, Igor Fedorov, Bilge Soran, Dhruv Choudhary, Raghuraman Krishnamoorthi, Vikas Chandra, Yuandong Tian, and Tijmen Blankevoort. 2025. Spinquant: Llm quantization with learned rotations. Preprint, arXiv:2405.16406. — [arXiv:2405.16406](https://arxiv.org/abs/2405.16406) [find](https://scholar.google.com/scholar?q=Zechun+Liu%2C+Changsheng+Zhao%2C+Igor+Fedorov%2C+Bilge+Soran%2C+Dhruv+Choudhary%2C+Raghuraman+Krishnamoorthi%2C+Vikas+Chandra%2C+Yuandong+Tian%2C+and+Tijmen+Blankevoort%2E+2025%2E+Spinquant%3A+Llm+quantization+with+learned)
19. Stephen Merity, Caiming Xiong, James Bradbury, and Richard Socher. 2016. [Pointer sentinel mixture models](https://md.research.elamur.ai/free/en/papers/merity-2016-pointer-sentinel-mixture-models/). arXiv preprint arXiv:1609.07843.
20. Denis Paperno, Germán Kruszewski, Angeliki Lazaridou, Quan Ngoc Pham, Raffaella Bernardi, Sandro Pezzelle, Marco Baroni, Gemma Boleda, and Raquel Fernández. 2016. [The lambada dataset: Word prediction requiring a broad discourse context](https://md.research.elamur.ai/free/en/papers/paperno-2016-lambada-dataset-word-prediction-requiring/). Preprint, arXiv:1606.06031.
21. Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. 2023. [Exploring the limits of transfer learning with a unified text-to-text transformer](https://md.research.elamur.ai/free/en/papers/raffel-2019-exploring-limits-transfer-learning-unified/). Preprint, arXiv:1910.10683.
22. Keisuke Sakaguchi, Ronan Le Bras, Chandra Bhagavatula, and Yejin Choi. 2019. Winogrande: An adversarial winograd schema challenge at scale. Preprint, arXiv:1907.10641. [find](https://scholar.google.com/scholar?q=Keisuke+Sakaguchi%2C+Ronan+Le+Bras%2C+Chandra+Bhagavatula%2C+and+Yejin+Choi%2E+2019%2E+Winogrande%3A+An+adversarial+winograd+schema+challenge+at+scale%2E+Preprint%2C+arXiv%3A1907%2E10641%2E)
23. Yuzhang Shang, Zhihang Yuan, Qiang Wu, and Zhen Dong. 2023. Pb-llm: Partially binarized large language models. Preprint, arXiv:2310.00034. — [arXiv:2310.00034](https://arxiv.org/abs/2310.00034) [find](https://scholar.google.com/scholar?q=Yuzhang+Shang%2C+Zhihang+Yuan%2C+Qiang+Wu%2C+and+Zhen+Dong%2E+2023%2E+Pb%2Dllm%3A+Partially+binarized+large+language+models%2E+Preprint%2C+arXiv%3A2310%2E00034%2E+%E2%80%94+%5BarXiv%3A2310%2E00034%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2310%2E00034%29)
24. Wenqi Shao, Mengzhao Chen, Zhaoyang Zhang, Peng Xu, Lirui Zhao, Zhiqian Li, Kaipeng Zhang, Peng Gao, Yu Qiao, and Ping Luo. 2024. [Omniquant: Omnidirectionally calibrated quantization for large language models](https://md.research.elamur.ai/free/en/papers/shao-2023-omniquant-omnidirectionally-calibrated-quantization-large/). Preprint, arXiv:2308.13137.
25. Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, Aurelien Rodriguez, Armand Joulin, Edouard Grave, and Guillaume Lample. 2023. [Llama: Open and efficient foundation language models](https://md.research.elamur.ai/free/en/papers/touvron-2023-llama-open-efficient-foundation-language/). Preprint…
26. Guangxuan Xiao, Ji Lin, Mickael Seznec, Hao Wu, Julien Demouth, and Song Han. 2024. Smoothquant: Accurate and efficient post-training quantization for large language models. Preprint, arXiv:2211.10438. [find](https://scholar.google.com/scholar?q=Guangxuan+Xiao%2C+Ji+Lin%2C+Mickael+Seznec%2C+Hao+Wu%2C+Julien+Demouth%2C+and+Song+Han%2E+2024%2E+Smoothquant%3A+Accurate+and+efficient+post%2Dtraining+quantization+for+large+language+models%2E+Preprint%2C+arXiv%3A2211%2E10438)
27. Jinying Xiao, Bin Ji, Shasha Li, Xiaodong Liu, Ma Jun, Ye Zhong, Wei Li, Xuan Xie, Qingbo Wu, and Jie Yu. 2025. Singlequant: Efficient quantization of large language models in a single pass. Preprint, arXiv:2511.22316. — [arXiv:2511.22316](https://arxiv.org/abs/2511.22316) [find](https://scholar.google.com/scholar?q=Jinying+Xiao%2C+Bin+Ji%2C+Shasha+Li%2C+Xiaodong+Liu%2C+Ma+Jun%2C+Ye+Zhong%2C+Wei+Li%2C+Xuan+Xie%2C+Qingbo+Wu%2C+and+Jie+Yu%2E+2025%2E+Singlequant%3A+Efficient+quantization+of+large+language+models+in+a+single+pass%2E+Preprint%2C)
28. Zukang Xu, Zhixiong Zhao, Xing Hu, Zhixuan Chen, and Dawei Yang. 2026. Kbvq-moe: Klt-guided svd with bias-corrected vector quantization for moe large language models. arXiv preprint arXiv:2602.11184. — [arXiv:2602.11184](https://arxiv.org/abs/2602.11184) [find](https://scholar.google.com/scholar?q=Zukang+Xu%2C+Zhixiong+Zhao%2C+Xing+Hu%2C+Zhixuan+Chen%2C+and+Dawei+Yang%2E+2026%2E+Kbvq%2Dmoe%3A+Klt%2Dguided+svd+with+bias%2Dcorrected+vector+quantization+for+moe+large+language+models%2E+arXiv+preprint+arXiv%3A2602%2E11184%2E+)
29. An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, Chujie Zheng, Dayiheng Liu, Fan Zhou, Fei Huang, Feng Hu, Hao Ge, Haoran Wei, Huan Lin, Jialong Tang, and 41 others. 2025. [Qwen3 technical report](https://md.research.elamur.ai/free/en/papers/yang-2025-qwen3-technical-report/). Preprint, arXiv:2505.09388.
30. Zijian Ye, Wei Huang, Yifei Yu, Tianhe Ren, Zhongrui Wang, and Xiaojuan Qi. 2025. Dbellquant: Breaking the bell with double-bell transformation for llms post training binarization. Preprint, arXiv:2507.01027. — [arXiv:2507.01027](https://arxiv.org/abs/2507.01027) [find](https://scholar.google.com/scholar?q=Zijian+Ye%2C+Wei+Huang%2C+Yifei+Yu%2C+Tianhe+Ren%2C+Zhongrui+Wang%2C+and+Xiaojuan+Qi%2E+2025%2E+Dbellquant%3A+Breaking+the+bell+with+double%2Dbell+transformation+for+llms+post+training+binarization%2E+Preprint%2C+arXiv%3A250)
31. Rowan Zellers, Ari Holtzman, Yonatan Bisk, Ali Farhadi, and Yejin Choi. 2019. Hellaswag: Can a machine really finish your sentence? Preprint, arXiv:1905.07830. [find](https://scholar.google.com/scholar?q=Rowan+Zellers%2C+Ari+Holtzman%2C+Yonatan+Bisk%2C+Ali+Farhadi%2C+and+Yejin+Choi%2E+2019%2E+Hellaswag%3A+Can+a+machine+really+finish+your+sentence%3F+Preprint%2C+arXiv%3A1905%2E07830%2E)
32. Zhixiong Zhao, Haomin Li, Fangxin Liu, Yuncheng Lu, Zongwu Wang, Tao Yang, Li Jiang, and Haibing Guan. 2025. Quark: Quantization-enabled circuit sharing for transformer acceleration by exploiting common patterns in nonlinear operations. In 2025 IEEE/ACM International Conference On Computer Aided Des… [find](https://scholar.google.com/scholar?q=Zhixiong+Zhao%2C+Haomin+Li%2C+Fangxin+Liu%2C+Yuncheng+Lu%2C+Zongwu+Wang%2C+Tao+Yang%2C+Li+Jiang%2C+and+Haibing+Guan%2E+2025%2E+Quark%3A+Quantization%2Denabled+circuit+sharing+for+transformer+acceleration+by+exploiting+comm)
33. Zhixiong Zhao, Fangxin Liu, Junjie Wang, Chenyang Guan, Zongwu Wang, Li Jiang, and Haibing Guan. 2026. Specquant: Spectral decomposition and adaptive truncation for ultra-low-bit llms quantization. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 40, pages 28786–28794. [find](https://scholar.google.com/scholar?q=Zhixiong+Zhao%2C+Fangxin+Liu%2C+Junjie+Wang%2C+Chenyang+Guan%2C+Zongwu+Wang%2C+Li+Jiang%2C+and+Haibing+Guan%2E+2026%2E+Specquant%3A+Spectral+decomposition+and+adaptive+truncation+for+ultra%2Dlow%2Dbit+llms+quantization%2E+In)
34. Albert Tseng, Jerry Chee, Qingyao Sun, Volodymyr Kuleshov, and Christopher De Sa. 2024. Quip\#: [find](https://scholar.google.com/scholar?q=Albert+Tseng%2C+Jerry+Chee%2C+Qingyao+Sun%2C+Volodymyr+Kuleshov%2C+and+Christopher+De+Sa%2E+2024%2E+Quip%5C%23%3A)

*Updated 2 November 2026*