---
title: "Profiling-Free Mixed-Precision Quantization for MoE LLMs via"
description: "Frameworks such as MxMoE build this sensitivity table by quantizing and measuring every expert–layer–bit combination, and… 41 references."
authors: ["Huachen Qi", "Ruiyu Zhuo", "Bowen Shi", "Xiang Chang", "Fei Chao", "Changjing Shang", "Qiang Shen"]
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.982/"
doi: "10.18653/v1/2026.acl-long.982"
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/qi-2026-profiling-free-mixed-precision-quantization/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/qi-2026-profiling-free-mixed-precision-quantization/)

[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/40/) / Profiling-Free Mixed-Precision Quantization for MoE LLMs via Fuzzy Rule Interpolation

# Profiling-Free Mixed-Precision Quantization for MoE LLMs via Fuzzy Rule Interpolation

**Authors:** Huachen Qi, Ruiyu Zhuo, [Bowen Shi](https://md.research.elamur.ai/free/en/authors/bowen-shi/), Xiang Chang, Fei Chao, Changjing Shang and Qiang Shen · **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.982/) · [PDF](https://aclanthology.org/2026.acl-long.982.pdf) · [DOI 10.18653/v1/2026.acl-long.982](https://doi.org/10.18653/v1/2026.acl-long.982) · [OpenAlex](https://openalex.org/W7166809838)

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

## Summary
Compressing Mixture-of-Experts LLMs with mixed-precision quantization depends on knowing how sensitive each expert, and each linear sub-layer inside it (gate, up, down), is to lower bit-widths. Frameworks such as MxMoE build this sensitivity table by quantizing and measuring every expert–layer–bit combination, and that cost grows linearly with the number of experts. FRI-MxMoE avoids full profiling. It measures quantization loss for only a small set of "anchor" experts and estimates the remaining configurations with Fuzzy Rule Interpolation. The rule base works over three intra-expert features: bit-width, activation variance and parameter scale. Experts that are routed to more often get higher weight in the objective. Bits are then allocated by Lagrangian relaxation rather than an ILP solver. The authors argue this choice tolerates noise in the predicted error surface better. Across several MoE families, accuracy stays equal to or slightly above MxMoE, while the profiling stage becomes much faster. The paper presents this as the first use of FRI in neural network quantization, making calibration of very large or fine-grained MoE models practical.

## Key points
- Profiling becomes up to 15.7× faster on DeepSeek-V2. Zero-shot accuracy gains about +1.04% on DeepSeek-V2-Lite compared with the MxMoE baseline.
- In the Qwen1.5-MoE ablation at the 3.25-bit setting, FRI combined with Lagrangian relaxation reaches 66.63 average accuracy and 6.94 PPL. MxMoE (full traversal with ILP) reaches 66.49 and 7.02. FRI combined with ILP scores 66.41.
- Allocating bits per linear block consistently beats allocating per expert. Removing or substituting individual features, such as activation statistics or weight scale, causes only small accuracy losses.
- The method has three main limitations:
  - The speedup shrinks on models with few experts, for example only 1.7× on Mixtral-8×22B.
  - Results depend on choosing representative anchors.
  - All experiments ran on A800 GPUs, so new hardware still requires some anchor profiling.
- Code is released at github.com/qi-h-c/Fri-MxMoE.

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

## Institutions

- [Xiamen University](https://md.research.elamur.ai/free/en/universities/xiamen-university/) — University, Xiamen, China · 21 works · 2,258 citations
- [Aberystwyth University](https://md.research.elamur.ai/free/en/universities/aberystwyth-university/) — University, Aberystwyth, United Kingdom · 2 works · 93 citations

📚 Shelves (6): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 2,869 works · [🧮 Computational Theory and Mathematics](https://md.research.elamur.ai/free/en/shelves/computer-science/computational-theory-and-mathematics/) · 252 works

🧭 Topics (1): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 3,320 works

## Cite

Cite as: Huachen Qi, Ruiyu Zhuo, Bowen Shi, Xiang Chang, Fei Chao, Changjing Shang and Qiang Shen. 2026. Profiling-Free Mixed-Precision Quantization for MoE LLMs via Fuzzy Rule Interpolation. 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{qi2026profiling,
  title = {{Profiling-Free Mixed-Precision Quantization for MoE LLMs via Fuzzy Rule Interpolation}},
  author = {Huachen Qi, Ruiyu Zhuo, Bowen Shi, Xiang Chang, Fei Chao, Changjing Shang and Qiang Shen},
  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.982},
  url = {https://doi.org/10.18653/v1/2026.acl-long.982}
}
```

- [← previous Profiling Psychopathic Behavior Using Machine Learning](https://md.research.elamur.ai/free/en/papers/treistman-2026-profiling-psychopathic-behavior-machine-learning/)
- [next → Program Structure-aware Language Models: Targeted Software Testing beyond Textual Semantics](https://md.research.elamur.ai/free/en/papers/tran-2026-program-structure-aware-language-models/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/40/)

## References

41 references, 8 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. task needs more experts: Dynamic routing in MoE models. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 12883–12895, Bangkok, Thailand. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=task+needs+more+experts%3A+Dynamic+routing+in+MoE+models%2E+In+Proceedings+of+the+62nd+Annual+Meeting+of+the+Association+for+Computational+Linguistics+%28Volume+1%3A+Long+Papers%29%2C+pages+12883%E2%80%9312895%2C+Bangkok%2C+)
2. P. Baranyi, L.T. Koczy, and T.D. Gedeon. 2004. A generalized concept for fuzzy rule interpolation. IEEE Transactions on Fuzzy Systems, 12(6):820–837. [find](https://scholar.google.com/scholar?q=P%2E+Baranyi%2C+L%2ET%2E+Koczy%2C+and+T%2ED%2E+Gedeon%2E+2004%2E+A+generalized+concept+for+fuzzy+rule+interpolation%2E+IEEE+Transactions+on+Fuzzy+Systems%2C+12%286%29%3A820%E2%80%93837%2E)
3. Yonatan Bisk, Rowan Zellers, Ronan Le bras, Jianfeng Gao, and Yejin Choi. 2020. [Piqa: Reasoning about physical commonsense in natural language](https://md.research.elamur.ai/free/en/papers/bisk-2019-piqa-reasoning-about-physical-commonsense/). Proceedings of the AAAI Conference on Artificial Intelligence, 34(05):7432–7439.
4. Yuanteng Chen, Yuantian Shao, Peisong Wang, and Jian Cheng. 2025. EAC-MoE: Expert-selection aware compressor for mixture-of-experts large language models. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 12942–12963, Vienna, Au… [find](https://scholar.google.com/scholar?q=Yuanteng+Chen%2C+Yuantian+Shao%2C+Peisong+Wang%2C+and+Jian+Cheng%2E+2025%2E+EAC%2DMoE%3A+Expert%2Dselection+aware+compressor+for+mixture%2Dof%2Dexperts+large+language+models%2E+In+Proceedings+of+the+63rd+Annual+Meeting+of+)
5. Yoonjun Cho, Soeun Kim, Dongjae Jeon, Kyelim Lee, Beomsoo Lee, and Albert No. 2025. Assigning distinct roles to quantized and low-rank matrices toward optimal weight decomposition. In Findings of the Association for Computational Linguistics: ACL 2025, pages 14453–14470, Vienna, Austria. Association… [find](https://scholar.google.com/scholar?q=Yoonjun+Cho%2C+Soeun+Kim%2C+Dongjae+Jeon%2C+Kyelim+Lee%2C+Beomsoo+Lee%2C+and+Albert+No%2E+2025%2E+Assigning+distinct+roles+to+quantized+and+low%2Drank+matrices+toward+optimal+weight+decomposition%2E+In+Findings+of+the+)
6. 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.
7. Nan Du, Yanping Huang, Andrew M Dai, Simon Tong, Dmitry Lepikhin, Yuanzhong Xu, Maxim Krikun, Yanqi Zhou, Adams Wei Yu, Orhan Firat, Barret Zoph, Liam Fedus, Maarten P Bosma, Zongwei Zhou, Tao Wang, Emma Wang, Kellie Webster, Marie Pellat, Kevin Robinson, and 8 others. 2022. [GLaM: Efficient scaling…](https://md.research.elamur.ai/free/en/papers/du-2021-glam-efficient-scaling-language-models/)
8. William Fedus, Barret Zoph, and Noam Shazeer. 2022. Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity. Journal of Machine Learning Research, 23(120):1–39. [find](https://scholar.google.com/scholar?q=William+Fedus%2C+Barret+Zoph%2C+and+Noam+Shazeer%2E+2022%2E+Switch+transformers%3A+Scaling+to+trillion+parameter+models+with+simple+and+efficient+sparsity%2E+Journal+of+Machine+Learning+Research%2C+23%28120%29%3A1%E2%80%9339%2E)
9. Elias Frantar and Dan Alistarh. 2023. Qmoe: Practical sub-1-bit compression of trillion-parameter models. Preprint, arXiv:2310.16795. [find](https://scholar.google.com/scholar?q=Elias+Frantar+and+Dan+Alistarh%2E+2023%2E+Qmoe%3A+Practical+sub%2D1%2Dbit+compression+of+trillion%2Dparameter+models%2E+Preprint%2C+arXiv%3A2310%2E16795%2E)
10. 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)
11. Fei Gao. 2023. Density-based approach for fuzzy rule interpolation. Applied Soft Computing, 143:110402. [find](https://scholar.google.com/scholar?q=Fei+Gao%2E+2023%2E+Density%2Dbased+approach+for+fuzzy+rule+interpolation%2E+Applied+Soft+Computing%2C+143%3A110402%2E)
12. Quzhe Huang, Zhenwei An, Nan Zhuang, Mingxu Tao, Chen Zhang, Yang Jin, Kun Xu, Kun Xu, Liwei Chen, Songfang Huang, and Yansong Feng. 2024a. [find](https://scholar.google.com/scholar?q=Quzhe+Huang%2C+Zhenwei+An%2C+Nan+Zhuang%2C+Mingxu+Tao%2C+Chen+Zhang%2C+Yang+Jin%2C+Kun+Xu%2C+Kun+Xu%2C+Liwei+Chen%2C+Songfang+Huang%2C+and+Yansong+Feng%2E+2024a%2E)
13. Harder Xijie Huang, Zechun Liu, Shih-Yang Liu, and Kwang-Ting Cheng. 2024b. RoLoRA: Fine-tuning rotated outlier-free LLMs for effective weight-activation quantization. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 7563– 7576, Miami, Florida, USA. Association for Com… [find](https://scholar.google.com/scholar?q=Harder+Xijie+Huang%2C+Zechun+Liu%2C+Shih%2DYang+Liu%2C+and+Kwang%2DTing+Cheng%2E+2024b%2E+RoLoRA%3A+Fine%2Dtuning+rotated+outlier%2Dfree+LLMs+for+effective+weight%2Dactivation+quantization%2E+In+Findings+of+the+Association+f)
14. Changhong Jiang, Changjing Shang, and Qiang Shen. 2025. Reinforcing tsk model interpolation with rule weight adjustment via location view analysis. IEEE Transactions on Fuzzy Systems, 33(2):580–592. [find](https://scholar.google.com/scholar?q=Changhong+Jiang%2C+Changjing+Shang%2C+and+Qiang+Shen%2E+2025%2E+Reinforcing+tsk+model+interpolation+with+rule+weight+adjustment+via+location+view+analysis%2E+IEEE+Transactions+on+Fuzzy+Systems%2C+33%282%29%3A580%E2%80%93592%2E)
15. Szilveszter Kovács and László T Kóczy. 1997. Approximate fuzzy reasoning based on interpolation in the vague environment of the fuzzy rule base as a practical alternative of the classical cri. In Proceedings of the 7th International Fuzzy Systems Association World Congress, Prague, Czech Republic, p… [find](https://scholar.google.com/scholar?q=Szilveszter+Kov%C3%A1cs+and+L%C3%A1szl%C3%B3+T+K%C3%B3czy%2E+1997%2E+Approximate+fuzzy+reasoning+based+on+interpolation+in+the+vague+environment+of+the+fuzzy+rule+base+as+a+practical+alternative+of+the+classical+cri%2E+In+Proc)
16. LászlóT. Kóczy and Kaoru Hirota. 1993a. Approximate reasoning by linear rule interpolation and general approximation. International Journal of Approximate Reasoning, 9(3):197–225. [find](https://scholar.google.com/scholar?q=L%C3%A1szl%C3%B3T%2E+K%C3%B3czy+and+Kaoru+Hirota%2E+1993a%2E+Approximate+reasoning+by+linear+rule+interpolation+and+general+approximation%2E+International+Journal+of+Approximate+Reasoning%2C+9%283%29%3A197%E2%80%93225%2E)
17. LászlóT. Kóczy and Kaoru Hirota. 1993b. Interpolative reasoning with insufficient evidence in sparse fuzzy rule bases. Information Sciences, 71(1):169–201. [find](https://scholar.google.com/scholar?q=L%C3%A1szl%C3%B3T%2E+K%C3%B3czy+and+Kaoru+Hirota%2E+1993b%2E+Interpolative+reasoning+with+insufficient+evidence+in+sparse+fuzzy+rule+bases%2E+Information+Sciences%2C+71%281%29%3A169%E2%80%93201%2E)
18. Dmitry Lepikhin, HyoukJoong Lee, Yuanzhong Xu, Dehao Chen, Orhan Firat, Yanping Huang, Maxim Krikun, Noam Shazeer, and Zhifeng Chen. 2020. Gshard: Scaling giant models with conditional computation and automatic sharding. Preprint, arXiv:2006.16668. [find](https://scholar.google.com/scholar?q=Dmitry+Lepikhin%2C+HyoukJoong+Lee%2C+Yuanzhong+Xu%2C+Dehao+Chen%2C+Orhan+Firat%2C+Yanping+Huang%2C+Maxim+Krikun%2C+Noam+Shazeer%2C+and+Zhifeng+Chen%2E+2020%2E+Gshard%3A+Scaling+giant+models+with+conditional+computation+and)
19. Baohao Liao, Christian Herold, Shahram Khadivi, and Christof Monz. 2024. ApiQ: Finetuning of 2-bit quantized large language model. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 20996–21020, Miami, Florida, USA. Association for Computational Linguist… [find](https://scholar.google.com/scholar?q=Baohao+Liao%2C+Christian+Herold%2C+Shahram+Khadivi%2C+and+Christof+Monz%2E+2024%2E+ApiQ%3A+Finetuning+of+2%2Dbit+quantized+large+language+model%2E+In+Proceedings+of+the+2024+Conference+on+Empirical+Methods+in+Natural)
20. 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 on-device llm compression and acceleration. In Proceedings of Machine Learning and Systems, volume 6, pages 87–100. [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+on%2Ddevice+llm+c)
21. Ka Man Lo, Zeyu Huang, Zihan Qiu, Zili Wang, and Jie Fu. 2025. A closer look into mixture-of-experts in large language models. In Findings of the Association for Computational Linguistics: NAACL 2025, pages 4427–4447, Albuquerque, New Mexico. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Ka+Man+Lo%2C+Zeyu+Huang%2C+Zihan+Qiu%2C+Zili+Wang%2C+and+Jie+Fu%2E+2025%2E+A+closer+look+into+mixture%2Dof%2Dexperts+in+large+language+models%2E+In+Findings+of+the+Association+for+Computational+Linguistics%3A+NAACL+2025%2C)
22. Ang Lv, Jin Ma, Yiyuan Ma, and Siyuan Qiao. 2026. Coupling experts and routers in mixture-of-experts via an auxiliary loss. Preprint, arXiv:2512.23447. — [arXiv:2512.23447](https://arxiv.org/abs/2512.23447) [find](https://scholar.google.com/scholar?q=Ang+Lv%2C+Jin+Ma%2C+Yiyuan+Ma%2C+and+Siyuan+Qiao%2E+2026%2E+Coupling+experts+and+routers+in+mixture%2Dof%2Dexperts+via+an+auxiliary+loss%2E+Preprint%2C+arXiv%3A2512%2E23447%2E+%E2%80%94+%5BarXiv%3A2512%2E23447%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2512%2E)
23. Yuexiao Ma, Taisong Jin, Xiawu Zheng, Yan Wang, Huixia Li, Yongjian Wu, Guannan Jiang, Wei Zhang, and Rongrong Ji. 2023a. Ompq: Orthogonal mixed precision quantization. Proceedings of the AAAI Conference on Artificial Intelligence, 37(7):9029–9037. [find](https://scholar.google.com/scholar?q=Yuexiao+Ma%2C+Taisong+Jin%2C+Xiawu+Zheng%2C+Yan+Wang%2C+Huixia+Li%2C+Yongjian+Wu%2C+Guannan+Jiang%2C+Wei+Zhang%2C+and+Rongrong+Ji%2E+2023a%2E+Ompq%3A+Orthogonal+mixed+precision+quantization%2E+Proceedings+of+the+AAAI+Confere)
24. Yuexiao Ma, Huixia Li, Xiawu Zheng, Feng Ling, Xuefeng Xiao, Rui Wang, Shilei Wen, Fei Chao, and Rongrong Ji. 2024a. Affinequant: Affine transformation quantization for large language models. Preprint, arXiv:2403.12544. — [arXiv:2403.12544](https://arxiv.org/abs/2403.12544) [find](https://scholar.google.com/scholar?q=Yuexiao+Ma%2C+Huixia+Li%2C+Xiawu+Zheng%2C+Feng+Ling%2C+Xuefeng+Xiao%2C+Rui+Wang%2C+Shilei+Wen%2C+Fei+Chao%2C+and+Rongrong+Ji%2E+2024a%2E+Affinequant%3A+Affine+transformation+quantization+for+large+language+models%2E+Preprint)
25. Yuexiao Ma, Huixia Li, Xiawu Zheng, Feng Ling, Xuefeng Xiao, Rui Wang, Shilei Wen, Fei Chao, and Rongrong Ji. 2024b. Outlier-aware slicing for post-training quantization in vision transformer. In Forty-first International Conference on Machine Learning. [find](https://scholar.google.com/scholar?q=Yuexiao+Ma%2C+Huixia+Li%2C+Xiawu+Zheng%2C+Feng+Ling%2C+Xuefeng+Xiao%2C+Rui+Wang%2C+Shilei+Wen%2C+Fei+Chao%2C+and+Rongrong+Ji%2E+2024b%2E+Outlier%2Daware+slicing+for+post%2Dtraining+quantization+in+vision+transformer%2E+In+Fort)
26. Yuexiao Ma, Huixia Li, Xiawu Zheng, Xuefeng Xiao, Rui Wang, Shilei Wen, Xin Pan, Fei Chao, and Rongrong Ji. 2023b. Solving oscillation problem in post-training quantization through a theoretical perspective. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages… [find](https://scholar.google.com/scholar?q=Yuexiao+Ma%2C+Huixia+Li%2C+Xiawu+Zheng%2C+Xuefeng+Xiao%2C+Rui+Wang%2C+Shilei+Wen%2C+Xin+Pan%2C+Fei+Chao%2C+and+Rongrong+Ji%2E+2023b%2E+Solving+oscillation+problem+in+post%2Dtraining+quantization+through+a+theoretical+persp)
27. 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/). Preprint, arXiv:1609.07843.
28. Markus Nagel, Rana Ali Amjad, Mart Van Baalen, Christos Louizos, and Tijmen Blankevoort. 2020. Up or down? Adaptive rounding for post-training quantization. In ICML, volume 119 of Proceedings of Machine Learning Research, pages 7197–7206. PMLR. [find](https://scholar.google.com/scholar?q=Markus+Nagel%2C+Rana+Ali+Amjad%2C+Mart+Van+Baalen%2C+Christos+Louizos%2C+and+Tijmen+Blankevoort%2E+2020%2E+Up+or+down%3F+Adaptive+rounding+for+post%2Dtraining+quantization%2E+In+ICML%2C+volume+119+of+Proceedings+of+Machi)
29. Denis Paperno, Germán Kruszewski, Angeliki Lazaridou, Ngoc Quan Pham, Raffaella Bernardi, Sandro Pezzelle, Marco Baroni, Gemma Boleda, and Raquel Fernandez. 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/). In ACL, pages 1525–1534.
30. Irina Proskurina, Luc Brun, Guillaume Metzler, and Julien Velcin. 2024. When quantization affects confidence of large language models? In Findings of the Association for Computational Linguistics: NAACL 2024, pages 1918–1928, Mexico City, Mexico. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Irina+Proskurina%2C+Luc+Brun%2C+Guillaume+Metzler%2C+and+Julien+Velcin%2E+2024%2E+When+quantization+affects+confidence+of+large+language+models%3F+In+Findings+of+the+Association+for+Computational+Linguistics%3A+NAA)
31. Zihan Qiu, Zeyu Huang, Bo Zheng, Kaiyue Wen, Zekun Wang, Rui Men, Ivan Titov, Dayiheng Liu, Jingren Zhou, and Junyang Lin. 2025. [Demons in the detail: On implementing load balancing loss for training specialized mixture-of-expert models](https://md.research.elamur.ai/free/en/papers/qiu-2025-demons-detail-implementing-load-balancing/). In Proceedings of the 63rd Annual Meeting of the Association f…
32. Yanpeng Qu, Jiaxing Wu, Zhanwen Wu, and Longzhi Yang. 2024. Fuzzy rule interpolation with a general representation of fuzzy sets. In 2024 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), pages 1–8. [find](https://scholar.google.com/scholar?q=Yanpeng+Qu%2C+Jiaxing+Wu%2C+Zhanwen+Wu%2C+and+Longzhi+Yang%2E+2024%2E+Fuzzy+rule+interpolation+with+a+general+representation+of+fuzzy+sets%2E+In+2024+IEEE+International+Conference+on+Fuzzy+Systems+%28FUZZ%2DIEEE%29%2C+pa)
33. Samyam Rajbhandari, Conglong Li, Zhewei Yao, Minjia Zhang, Reza Yazdani Aminabadi, Ammar Ahmad Awan, Jeff Rasley, and Yuxiong He. 2022. [DeepSpeed-MoE: Advancing mixture-of-experts inference and training to power next-generation AI scale](https://md.research.elamur.ai/free/en/papers/rajbhandari-2022-deepspeed-moe-advancing-mixture-experts/). In ICML, volume 162 of Proceedings of Machine Learning Researc…
34. Keisuke Sakaguchi, Ronan Le Bras, Chandra Bhagavatula, and Yejin Choi. 2021. Winogrande: an adversarial winograd schema challenge at scale. Commun. ACM, 64(9):99–106. [find](https://scholar.google.com/scholar?q=Keisuke+Sakaguchi%2C+Ronan+Le+Bras%2C+Chandra+Bhagavatula%2C+and+Yejin+Choi%2E+2021%2E+Winogrande%3A+an+adversarial+winograd+schema+challenge+at+scale%2E+Commun%2E+ACM%2C+64%289%29%3A99%E2%80%93106%2E)
35. Wei Tao, Haocheng Lu, Xiaoyang Qu, Bin Zhang, Kai Lu, Jiguang Wan, and Jianzong Wang. 2025. Mo-QAE: Mixed-precision quantization for long-context LLM inference via mixture of quantization-aware experts. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volum… [find](https://scholar.google.com/scholar?q=Wei+Tao%2C+Haocheng+Lu%2C+Xiaoyang+Qu%2C+Bin+Zhang%2C+Kai+Lu%2C+Jiguang+Wan%2C+and+Jianzong+Wang%2E+2025%2E+Mo%2DQAE%3A+Mixed%2Dprecision+quantization+for+long%2Dcontext+LLM+inference+via+mixture+of+quantization%2Daware+expert)
36. An Wang, Xingwu Sun, Ruobing Xie, Shuaipeng Li, Jiaqi Zhu, Zhen Yang, Pinxue Zhao, Weidong Han, Zhanhui Kang, Di Wang, Naoaki Okazaki, and Cheng-zhong Xu. 2025. [HMoE: Heterogeneous mixture of experts for language modeling](https://md.research.elamur.ai/free/en/papers/wang-2025-hmoe-heterogeneous-mixture-experts-language/). In EMNLP, pages 21943–21957, Suzhou, China. Association for Computational Lin…
37. Kuan Wang, Zhijian Liu, Yujun Lin, Ji Lin, and Song Han. 2019. Haq: Hardware-aware automated quantization with mixed precision. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). [find](https://scholar.google.com/scholar?q=Kuan+Wang%2C+Zhijian+Liu%2C+Yujun+Lin%2C+Ji+Lin%2C+and+Song+Han%2E+2019%2E+Haq%3A+Hardware%2Daware+automated+quantization+with+mixed+precision%2E+In+Proceedings+of+the+IEEE%2FCVF+Conference+on+Computer+Vision+and+Pattern)
38. Xiuying Wei, Yunchen Zhang, Yuhang Li, Xiangguo Zhang, Ruihao Gong, Jinyang Guo, and Xianglong Liu. 2023. Outlier suppression+: Accurate quantization of large language models by equivalent and effective shifting and scaling. In EMNLP, Singapore. [find](https://scholar.google.com/scholar?q=Xiuying+Wei%2C+Yunchen+Zhang%2C+Yuhang+Li%2C+Xiangguo+Zhang%2C+Ruihao+Gong%2C+Jinyang+Guo%2C+and+Xianglong+Liu%2E+2023%2E+Outlier+suppression%2B%3A+Accurate+quantization+of+large+language+models+by+equivalent+and+effecti)
39. Zhanhao Xie, Yuexiao Ma, Xiawu Zheng, Fei Chao, Wanchen Sui, Yong Li, Shen Li, and Rongrong Ji. 2025. Automated fine-grained mixture-of-experts quantization. In Findings of ACL. [find](https://scholar.google.com/scholar?q=Zhanhao+Xie%2C+Yuexiao+Ma%2C+Xiawu+Zheng%2C+Fei+Chao%2C+Wanchen+Sui%2C+Yong+Li%2C+Shen+Li%2C+and+Rongrong+Ji%2E+2025%2E+Automated+fine%2Dgrained+mixture%2Dof%2Dexperts+quantization%2E+In+Findings+of+ACL%2E)
40. Rowan Zellers, Ari Holtzman, Yonatan Bisk, Ali Farhadi, and Yejin Choi. 2019. HellaSwag: Can a machine really finish your sentence? In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 4791–4800, Florence, Italy. Association for Computational Linguistics. [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+In+Proceedings+of+the+57th+Annual+Meeting+of+the+Association+for+Com)
41. Jiaqi Zhao, Miao Zhang, Chao Zeng, Ming Wang, Xuebo Liu, and Liqiang Nie. 2024. LRQuant: Learnable and robust post-training quantization for large language models. In ACL, pages 2240–2255. [find](https://scholar.google.com/scholar?q=Jiaqi+Zhao%2C+Miao+Zhang%2C+Chao+Zeng%2C+Ming+Wang%2C+Xuebo+Liu%2C+and+Liqiang+Nie%2E+2024%2E+LRQuant%3A+Learnable+and+robust+post%2Dtraining+quantization+for+large+language+models%2E+In+ACL%2C+pages+2240%E2%80%932255%2E)

*Updated 1 November 2026*