---
title: "TokenTiming — paper by Xiao et al. (2026) — summary and ideas"
description: "The authors propose TokenTiming, which works with any pair of off-the-shelf models and needs no retraining. 35 references."
authors: ["Sibo Xiao", "Fu Jinyuan", "Zhongle Xie", "Lidan Shou"]
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.1983/"
doi: "10.18653/v1/2026.acl-long.1983"
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/xiao-2026-tokentiming-dynamic-alignment-method-universal/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/xiao-2026-tokentiming-dynamic-alignment-method-universal/)

[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/53/) / TokenTiming: A Dynamic Alignment Method for Universal Speculative Decoding Model Pairs

# TokenTiming: A Dynamic Alignment Method for Universal Speculative Decoding Model Pairs

**Authors:** Sibo Xiao, Fu Jinyuan, [Zhongle Xie](https://md.research.elamur.ai/free/en/authors/zhongle-xie/) and [Lidan Shou](https://md.research.elamur.ai/free/en/authors/lidan-shou/) · **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.1983/) · [PDF](https://aclanthology.org/2026.acl-long.1983.pdf) · [DOI 10.18653/v1/2026.acl-long.1983](https://doi.org/10.18653/v1/2026.acl-long.1983) · [OpenAlex](https://openalex.org/W7166854755)

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

## Summary

Speculative decoding (SD) speeds up LLM inference by letting a small draft model propose tokens that a large target model then checks. Standard SD only works when both models use the same vocabulary. This limits which draft models can be used and often forces teams to train a dedicated drafter. Earlier cross-vocabulary methods fall short: SLEM cannot do probabilistic sampling, and TLI depends on how much the two vocabularies overlap.

The authors propose TokenTiming, which works with any pair of off-the-shelf models and needs no retraining. At each step, the draft tokens are decoded to a string and re-tokenized with the target tokenizer, producing proxy target tokens. Dynamic Token Warping, an adaptation of Dynamic Time Warping, then builds a many-to-many alignment between the two token sequences. The draft probabilities are carried over along this alignment so that standard speculative sampling can verify them. Experiments on summarization, translation, code and math show speedups of up to 1.57× over autoregressive decoding, with better results than TLI. This makes choosing a draft model much more flexible.

## Key points

- **Alignment method:** Token distance is measured with Levenshtein distance, and a Sakoe-Chiba band of width w restricts the search. This cuts alignment cost from O(k·m) to roughly O(w·max(k, m)).
- **Larger models:** On 7B/33B target models, TokenTiming reaches a 2.27× speedup, close to Medusa and EAGLE-1/2, which require same-vocabulary drafters.
- **Draft model strength matters:** Stronger drafters (Qwen2.5-0.5B, Qwen3-0.6B) exceed 2× on reasoning-heavy tasks. Weaker ones (OPT-350M, Vicuna-68M) give smaller gains but still outperform TLI.
- **Overhead:** Alignment adds only 0.1–0.5% of total runtime, about 663µs of blocking per decoding cycle.
- **Evaluation and limitations:** About 15% of samples involving repetitive loops were excluded to avoid inflated speedups. The probability transfer is one-hot (top-1 token only), and alignment works at the character level rather than the semantic level, so effectiveness varies across languages.

*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

- [Zhejiang University](https://md.research.elamur.ai/free/en/universities/zhejiang-university/) — University, Hangzhou, China · 224 works · 13,587 citations

📚 Shelves (4): [🖥️ 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

🧭 Topics (1): [🪶 Efficient models & compression](https://md.research.elamur.ai/free/en/topics/efficient-models/) · 297 works

## Cite

Cite as: Sibo Xiao, Fu Jinyuan, Zhongle Xie and Lidan Shou. 2026. TokenTiming: A Dynamic Alignment Method for Universal Speculative Decoding Model Pairs. 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{xiao2026tokentiming,
  title = {{TokenTiming: A Dynamic Alignment Method for Universal Speculative Decoding Model Pairs}},
  author = {Sibo Xiao, Fu Jinyuan, Zhongle Xie and Lidan Shou},
  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.1983},
  url = {https://doi.org/10.18653/v1/2026.acl-long.1983}
}
```

- [← previous TokenPenalty: Alleviating Attention Sinks and Positional Decay in LVLMs](https://md.research.elamur.ai/free/en/papers/zhang-2026-tokenpenalty-alleviating-attention-sinks-positional/)
- [next → ToMELP: A Theory-of-Mind Benchmark for Route-Controlled Persuasion under the Elaboration Likelihood Model](https://md.research.elamur.ai/free/en/papers/wang-2026-tomelp-theory-mind-benchmark-route/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/53/)

## References

35 references, 19 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Marah Abdin, Jyoti Aneja, Harkirat Behl, Sébastien Bubeck, Ronen Eldan, Suriya Gunasekar, Michael Harrison, Russell J. Hewett, Mojan Javaheripi, Piero Kauffmann, James R. Lee, Yin Tat Lee, Yuanzhi Li, Weishung Liu, Caio C. T. Mendes, Anh Nguyen, Eric Price, Gustavo de Rosa, Olli Saarikivi, and 8 oth… — [Phi-4 Technical Report](https://md.research.elamur.ai/free/en/papers/abdin-2024-phi-4-technical-report/)
2. Zachary Ankner, Rishab Parthasarathy, Aniruddha Nrusimha, Christopher Rinard, Jonathan Ragan-Kelley, and William Brandon. 2024. Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding. Preprint, arXiv:2402.05109. — [arXiv:2402.05109](https://arxiv.org/abs/2402.05109) [find](https://scholar.google.com/scholar?q=Zachary+Ankner%2C+Rishab+Parthasarathy%2C+Aniruddha+Nrusimha%2C+Christopher+Rinard%2C+Jonathan+Ragan%2DKelley%2C+and+William+Brandon%2E+2024%2E+Hydra%3A+Sequentially%2DDependent+Draft+Heads+for+Medusa+Decoding%2E+Preprint%2C)
3. Tianle Cai, Yuhong Li, Zhengyang Geng, Hongwu Peng, Jason D Lee, Deming Chen, and Tri Dao. 2024. [Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads](https://md.research.elamur.ai/free/en/papers/cai-2024-medusa-simple-llm-inference-acceleration/). Preprint, arXiv:2401.10774.
4. Charlie Chen, Sebastian Borgeaud, Geoffrey Irving, Jean-Baptiste Lespiau, Laurent Sifre, and John Jumper. 2023. Accelerating large language model decoding with speculative sampling. arXiv preprint arXiv:2302.01318. [find](https://scholar.google.com/scholar?q=Charlie+Chen%2C+Sebastian+Borgeaud%2C+Geoffrey+Irving%2C+Jean%2DBaptiste+Lespiau%2C+Laurent+Sifre%2C+and+John+Jumper%2E+2023%2E+Accelerating+large+language+model+decoding+with+speculative+sampling%2E+arXiv+preprint+arX)
5. Jian Chen, Vashisth Tiwari, Ranajoy Sadhukhan, Zhuoming Chen, Jinyuan Shi, Ian En-Hsu Yen, and Beidi Chen. 2024. Magicdec: Breaking the latency-throughput tradeoff for long context generation with speculative decoding. arXiv preprint arXiv:2408.11049. — [arXiv:2408.11049](https://arxiv.org/abs/2408.11049) [find](https://scholar.google.com/scholar?q=Jian+Chen%2C+Vashisth+Tiwari%2C+Ranajoy+Sadhukhan%2C+Zhuoming+Chen%2C+Jinyuan+Shi%2C+Ian+En%2DHsu+Yen%2C+and+Beidi+Chen%2E+2024%2E+Magicdec%3A+Breaking+the+latency%2Dthroughput+tradeoff+for+long+context+generation+with+spe)
6. Karl Cobbe, Vineet Kosaraju, Mohammad Bavarian, Mark Chen, Heewoo Jun, Lukasz Kaiser, Matthias Plappert, Jerry Tworek, Jacob Hilton, Reiichiro Nakano, and 1 others. 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. DeepSeek-AI, Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, Xiaokang Zhang, Xingkai Yu, Yu Wu, Z. F. Wu, Zhibin Gou, Zhihong Shao, Zhuoshu Li, Ziyi Gao, and 181 others. 2025. [Deepseek-r1: Incentivizing reasoning capability in ll…](https://md.research.elamur.ai/free/en/papers/deepseek-ai-2025-deepseek-r1-incentivizing-reasoning-capability/)
8. Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Amy Yang, Angela Fan, and 1 others. 2024. [The llama 3 herd of models](https://md.research.elamur.ai/free/en/papers/grattafiori-2024-llama-3-herd-models/). arXiv preprint arXiv:2407.21783.
9. Yichao Fu, Peter Bailis, Ion Stoica, and Hao Zhang. 2024. [Break the Sequential Dependency of LLM Inference Using Lookahead Decoding](https://md.research.elamur.ai/free/en/papers/fu-2024-break-sequential-dependency-llm-inference/). Preprint, arXiv:2402.02057.
10. Aaron Grattafiori, Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Alex Vaughan, and 1 others. 2024. [The llama 3 herd of models](https://md.research.elamur.ai/free/en/papers/grattafiori-2024-llama-3-herd-models/). arXiv preprint arXiv:2407.21783.
11. Siqi Kou, Lanxiang Hu, Zhezhi He, Zhijie Deng, and Hao Zhang. 2024. CLLMs: Consistency Large Language Models. In Forty-first International Conference on Machine Learning. [find](https://scholar.google.com/scholar?q=Siqi+Kou%2C+Lanxiang+Hu%2C+Zhezhi+He%2C+Zhijie+Deng%2C+and+Hao+Zhang%2E+2024%2E+CLLMs%3A+Consistency+Large+Language+Models%2E+In+Forty%2Dfirst+International+Conference+on+Machine+Learning%2E)
12. Tom Kwiatkowski, Jennimaria Palomaki, Olivia Redfield, Michael Collins, Ankur Parikh, Chris Alberti, Danielle Epstein, Illia Polosukhin, Jacob Devlin, Kenton Lee, Kristina Toutanova, Llion Jones, Matthew Kelcey, Ming-Wei Chang, Andrew M. Dai, Jakob Uszkoreit, Quoc Le, and Slav Petrov. 2019. [Natural…](https://md.research.elamur.ai/free/en/papers/kwiatkowski-2019-natural-questions-benchmark-question-answering/)
13. Yaniv Leviathan, Matan Kalman, and Yossi Matias. 2023. Fast inference from transformers via speculative decoding. In International Conference on Machine Learning, pages 19274–19286. PMLR. [find](https://scholar.google.com/scholar?q=Yaniv+Leviathan%2C+Matan+Kalman%2C+and+Yossi+Matias%2E+2023%2E+Fast+inference+from+transformers+via+speculative+decoding%2E+In+International+Conference+on+Machine+Learning%2C+pages+19274%E2%80%9319286%2E+PMLR%2E)
14. Yuhui Li, Fangyun Wei, Chao Zhang, and Hongyang Zhang. 2024a. [EAGLE-2: Faster Inference of Language Models with Dynamic Draft Trees](https://md.research.elamur.ai/free/en/papers/li-2024-eagle-2-faster-inference-language/). Preprint, arXiv:2406.16858.
15. Yuhui Li, Fangyun Wei, Chao Zhang, and Hongyang Zhang. 2024b. [EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty](https://md.research.elamur.ai/free/en/papers/li-2024-eagle-speculative-sampling-requires-rethinking/). Preprint, arXiv:2401.15077.
16. Yuhui Li, Fangyun Wei, Chao Zhang, and Hongyang Zhang. 2025. EAGLE-3: Scaling Up Inference Acceleration of Large Language Models via Training-Time Test. Preprint, arXiv:2503.01840. — [arXiv:2503.01840](https://arxiv.org/abs/2503.01840) [find](https://scholar.google.com/scholar?q=Yuhui+Li%2C+Fangyun+Wei%2C+Chao+Zhang%2C+and+Hongyang+Zhang%2E+2025%2E+EAGLE%2D3%3A+Scaling+Up+Inference+Acceleration+of+Large+Language+Models+via+Training%2DTime+Test%2E+Preprint%2C+arXiv%3A2503%2E01840%2E+%E2%80%94+%5BarXiv%3A2503%2E01840)
17. Xiaoxuan Liu, Cade Daniel, Langxiang Hu, Woosuk Kwon, Zhuohan Li, Xiangxi Mo, Alvin Cheung, Zhijie Deng, Ion Stoica, and Hao Zhang. 2024. Optimizing Speculative Decoding for Serving Large Language Models using Goodput. Preprint, arXiv:2406.14066. [find](https://scholar.google.com/scholar?q=Xiaoxuan+Liu%2C+Cade+Daniel%2C+Langxiang+Hu%2C+Woosuk+Kwon%2C+Zhuohan+Li%2C+Xiangxi+Mo%2C+Alvin+Cheung%2C+Zhijie+Deng%2C+Ion+Stoica%2C+and+Hao+Zhang%2E+2024%2E+Optimizing+Speculative+Decoding+for+Serving+Large+Language+Mod)
18. Xupeng Miao, Gabriele Oliaro, Zhihao Zhang, Xinhao Cheng, Zeyu Wang, Zhengxin Zhang, Rae Ying Yee Wong, Alan Zhu, Lijie Yang, Xiaoxiang Shi, Chunan Shi, Zhuoming Chen, Daiyaan Arfeen, Reyna Abhyankar, and Zhihao Jia. 2024. Specinfer: Accelerating large language model serving with tree-based speculat… [find](https://scholar.google.com/scholar?q=Xupeng+Miao%2C+Gabriele+Oliaro%2C+Zhihao+Zhang%2C+Xinhao+Cheng%2C+Zeyu+Wang%2C+Zhengxin+Zhang%2C+Rae+Ying+Yee+Wong%2C+Alan+Zhu%2C+Lijie+Yang%2C+Xiaoxiang+Shi%2C+Chunan+Shi%2C+Zhuoming+Chen%2C+Daiyaan+Arfeen%2C+Reyna+Abhyankar%2C)
19. Ramesh Nallapati, Bowen Zhou, Cicero dos Santos, Çağlar Gu˙lçehre, and Bing Xiang. 2016. [Abstractive text summarization using sequence-to-sequence RNNs and beyond](https://md.research.elamur.ai/free/en/papers/nallapati-2016-abstractive-text-summarization-sequence-sequence/). In Proceedings of the 20th SIGNLL Conference on Computational Natural Language Learning, pages 280–290, Berlin, Germany. Association fo…
20. OpenAI. 2025. [gpt-oss-120b and gpt-oss-20b model card](https://md.research.elamur.ai/free/en/papers/agarwal-2025-gpt-oss-120b-gpt-oss/). Preprint, arXiv:2508.10925.
21. H. Sakoe and S. Chiba. 1978. Dynamic programming algorithm optimization for spoken word recognition. IEEE Transactions on Acoustics, Speech, and Signal Processing, 26(1):43–49. [find](https://scholar.google.com/scholar?q=H%2E+Sakoe+and+S%2E+Chiba%2E+1978%2E+Dynamic+programming+algorithm+optimization+for+spoken+word+recognition%2E+IEEE+Transactions+on+Acoustics%2C+Speech%2C+and+Signal+Processing%2C+26%281%29%3A43%E2%80%9349%2E)
22. Rico Sennrich, Barry Haddow, and Alexandra Birch. 2016. [Neural machine translation of rare words with subword units](https://md.research.elamur.ai/free/en/papers/sennrich-2016-neural-machine-translation-rare-words/). In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1715–1725, Berlin, Germany. Association for Computational Lin…
23. Zhihong Shao, Minlie Huang, Jiangtao Wen, Wenfei Xu, and Xiaoyan Zhu. 2019. Long and diverse text generation with planning-based hierarchical variational model. Preprint, arXiv:1908.06605. [find](https://scholar.google.com/scholar?q=Zhihong+Shao%2C+Minlie+Huang%2C+Jiangtao+Wen%2C+Wenfei+Xu%2C+and+Xiaoyan+Zhu%2E+2019%2E+Long+and+diverse+text+generation+with+planning%2Dbased+hierarchical+variational+model%2E+Preprint%2C+arXiv%3A1908%2E06605%2E)
24. Daria Soboleva, Faisal Al-Khateeb, Robert Myers, Jacob R Steeves, Joel Hestness, and Nolan Dey. 2023. SlimPajama: A 627B token cleaned and deduplicated version of RedPajama. [find](https://scholar.google.com/scholar?q=Daria+Soboleva%2C+Faisal+Al%2DKhateeb%2C+Robert+Myers%2C+Jacob+R+Steeves%2C+Joel+Hestness%2C+and+Nolan+Dey%2E+2023%2E+SlimPajama%3A+A+627B+token+cleaned+and+deduplicated+version+of+RedPajama%2E)
25. Ziteng Sun, Jae Hun Ro, Ahmad Beirami, and Ananda Theertha Suresh. 2024. Optimal block-level draft verification for accelerating speculative decoding. arXiv preprint arXiv:2403.10444. — [arXiv:2403.10444](https://arxiv.org/abs/2403.10444) [find](https://scholar.google.com/scholar?q=Ziteng+Sun%2C+Jae+Hun+Ro%2C+Ahmad+Beirami%2C+and+Ananda+Theertha+Suresh%2E+2024%2E+Optimal+block%2Dlevel+draft+verification+for+accelerating+speculative+decoding%2E+arXiv+preprint+arXiv%3A2403%2E10444%2E+%E2%80%94+%5BarXiv%3A2403%2E10)
26. Nadav Timor, Jonathan Mamou, Daniel Korat, Moshe Berchansky, Gaurav Jain, Oren Pereg, Moshe Wasserblat, and David Harel. 2025a. Accelerating llm inference with lossless speculative decoding algorithms for heterogeneous vocabularies. Preprint, arXiv:2502.05202. — [arXiv:2502.05202](https://arxiv.org/abs/2502.05202) [find](https://scholar.google.com/scholar?q=Nadav+Timor%2C+Jonathan+Mamou%2C+Daniel+Korat%2C+Moshe+Berchansky%2C+Gaurav+Jain%2C+Oren+Pereg%2C+Moshe+Wasserblat%2C+and+David+Harel%2E+2025a%2E+Accelerating+llm+inference+with+lossless+speculative+decoding+algorithms)
27. Nadav Timor, Jonathan Mamou, Daniel Korat, Moshe Berchansky, Oren Pereg, Moshe Wasserblat, Tomer Galanti, Michal Gordon, and David Harel. 2025b. Distributed speculative inference (dsi): Speculation parallelism for provably faster lossless language model inference. In International Conference on Lear… [find](https://scholar.google.com/scholar?q=Nadav+Timor%2C+Jonathan+Mamou%2C+Daniel+Korat%2C+Moshe+Berchansky%2C+Oren+Pereg%2C+Moshe+Wasserblat%2C+Tomer+Galanti%2C+Michal+Gordon%2C+and+David+Harel%2E+2025b%2E+Distributed+speculative+inference+%28dsi%29%3A+Speculation+pa)
28. Nadav Timor, Jonathan Mamou, Oren Pereg, Hongyang Zhang, and David Harel. 2025c. Out-of-vocabulary sampling boosts speculative decoding. Preprint, arXiv:2506.03206. — [arXiv:2506.03206](https://arxiv.org/abs/2506.03206) [find](https://scholar.google.com/scholar?q=Nadav+Timor%2C+Jonathan+Mamou%2C+Oren+Pereg%2C+Hongyang+Zhang%2C+and+David+Harel%2E+2025c%2E+Out%2Dof%2Dvocabulary+sampling+boosts+speculative+decoding%2E+Preprint%2C+arXiv%3A2506%2E03206%2E+%E2%80%94+%5BarXiv%3A2506%2E03206%5D%28https%3A%2F%2Farxiv%2E)
29. Changhan Wang, Kyunghyun Cho, and Jiatao Gu. 2019. [Neural machine translation with byte-level subwords](https://md.research.elamur.ai/free/en/papers/wang-2019-neural-machine-translation-byte-level/). Preprint, arXiv:1909.03341.
30. Heming Xia, Zhe Yang, Qingxiu Dong, Peiyi Wang, Yongqi Li, Tao Ge, Tianyu Liu, Wenjie Li, and Zhifang Sui. 2024. [Unlocking efficiency in large language model inference: A comprehensive survey of speculative decoding](https://md.research.elamur.ai/free/en/papers/xia-2024-unlocking-efficiency-large-language-model/). In Findings of the Association for Computational Linguistics ACL 2024, pages 7655–7…
31. Jin Xu, Xiaojiang Liu, Jianhao Yan, Deng Cai, Huayang Li, and Jian Li. 2022. Learning to break the loop: Analyzing and mitigating repetitions for neural text generation. Preprint, arXiv:2206.02369. — [arXiv:2206.02369](https://arxiv.org/abs/2206.02369) [find](https://scholar.google.com/scholar?q=Jin+Xu%2C+Xiaojiang+Liu%2C+Jianhao+Yan%2C+Deng+Cai%2C+Huayang+Li%2C+and+Jian+Li%2E+2022%2E+Learning+to+break+the+loop%3A+Analyzing+and+mitigating+repetitions+for+neural+text+generation%2E+Preprint%2C+arXiv%3A2206%2E02369%2E+%E2%80%94+)
32. 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.
33. Susan Zhang, Stephen Roller, Naman Goyal, Mikel Artetxe, Moya Chen, Shuohui Chen, Christopher Dewan, Mona Diab, Xian Li, Xi Victoria Lin, Todor Mihaylov, Myle Ott, Sam Shleifer, Kurt Shuster, Daniel Simig, Punit Singh Koura, Anjali Sridhar, Tianlu Wang, and Luke Zettlemoyer. 2022. [Opt: Open pre-trai…](https://md.research.elamur.ai/free/en/papers/zhang-2022-opt-open-pre-trained-transformer/)
34. Weilin Zhao, Tengyu Pan, Xu Han, Yudi Zhang, Ao Sun, Yuxiang Huang, Kaihuo Zhang, Weilun Zhao, Yuxuan Li, Jianyong Wang, and 1 others. 2025. [Fr-spec: Accelerating large-vocabulary language models via frequency-ranked speculative sampling](https://md.research.elamur.ai/free/en/papers/zhao-2025-fr-spec-accelerating-large-vocabulary/). arXiv preprint arXiv:2502.14856.
35. Lianmin Zheng, Wei-Lin Chiang, Ying Sheng, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Zi Lin, Zhuohan Li, Dacheng Li, Eric Xing, and 1 others. 2023. [Judging llm-as-a-judge with mt-bench and chatbot arena](https://md.research.elamur.ai/free/en/papers/zheng-2023-judging-llm-judge-mt-bench/). Advances in Neural Information Processing Systems, 36:46595–46623.

*Updated 2 November 2026*