--- title: "Xiaoxuan Liu — author profile and papers — Elamur Research" description: "Xiaoxuan Liu, Northwestern Polytechnical University: 2 papers on Elamur Research (2023–2024), h-index 21 — affiliations, topics, co-authors…" canonical: "https://research.elamur.ai/free/en/authors/xiaoxuan-liu/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/xiaoxuan-liu/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Xiaoxuan Liu # Xiaoxuan Liu Xiaoxuan Liu has 2 papers in our library, in 2023–2024, most of them on [GPU & parallel computing](https://md.research.elamur.ai/free/en/topics/gpu-parallel-computing/), [Efficient models & compression](https://md.research.elamur.ai/free/en/topics/efficient-models/); often with [Ion Gabriel Stoica](https://md.research.elamur.ai/free/en/authors/ion-gabriel-stoica/), [Alvin Cheung](https://md.research.elamur.ai/free/en/authors/alvin-cheung/), [Hao Zhang](https://md.research.elamur.ai/free/en/authors/hao-zhang/). 2 papers in our library · 2023–2024 [OpenAlex](https://openalex.org/A5100666862) · [ORCID](https://orcid.org/0000-0002-1426-5056) · [**h-index 21**](https://openalex.org/authors/A5100666862) · [89 works](https://openalex.org/works?filter=author.id:A5100666862) · [2,192 citations](https://openalex.org/works?filter=author.id:A5100666862&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [📄 2 works in our library](https://md.research.elamur.ai/free/en/authors/xiaoxuan-liu/#papers) · [🔗 Cited 156 times in our library](https://md.research.elamur.ai/free/en/authors/xiaoxuan-liu/cited-by/) · [2 more in our library without a page yet](#also) · [⭐ Paper Stars ranking: #8051](https://md.research.elamur.ai/free/en/paper-stars/page/81/#star-8051) The profile is the library's match of the name; two people with one name are not always told apart. Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Xiaoxuan+Liu) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Xiaoxuan+Liu) · [dblp](https://dblp.org/search?q=Xiaoxuan+Liu) · [ACL Anthology](https://aclanthology.org/search/?q=Xiaoxuan+Liu) ## Affiliations [🏛️**Chinese Academy of Sciences** Beijing · China 2021–2026 · 24 papers*current*](https://md.research.elamur.ai/free/en/government/chinese-academy-of-sciences/) · [🎓**Aerospace Information Research Institute** Beijing · China 2021–2026 · 20 papers*current*](https://md.research.elamur.ai/free/en/universities/aerospace-information-research-institute/) · [🎓**University of Chinese Academy of Sciences** Beijing · China 2024–2026 · 5 papers*current*](https://md.research.elamur.ai/free/en/universities/university-of-chinese-academy-of-sciences/) · [🏥**Qingdao Municipal Hospital** Qingdao · China 2026 · 3 papers*current*](https://ror.org/02jqapy19) · [🎓**Shaanxi University of Science and Technology** Xi'an · China 2025–2026 · 2 papers*current*](https://ror.org/034t3zs45) · [🎓**Northwestern Polytechnical University** Xi'an · China 2026 · 1 paper*current*](https://md.research.elamur.ai/free/en/universities/northwestern-polytechnical-university/) · [🎓**Tsinghua University** Beijing · China 2017–2024 · 25 papersEducation](https://md.research.elamur.ai/free/en/universities/tsinghua-university/) · [🎓**Sun Yat-sen University** Guangzhou · China 2020–2023 · 6 papers](https://md.research.elamur.ai/free/en/universities/sun-yat-sen-university/) · [🏥**Peking University Third Hospital** Beijing · China 2024–2025 · 4 papers](https://ror.org/04wwqze12) · [🔬**Research Center for Eco-Environmental Sciences** Beijing · China 2023–2025 · 3 papers](https://ror.org/03rpsvy57) From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 25 more institutions on single bylines are not listed. ## Fields, topics and concepts Of its works in our library, with the number of works on each. 📚 Shelves 6 The field of science this work belongs to (OpenAlex fields).[Arts and Humanities · 2 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · [Computer Science · 2 works](https://md.research.elamur.ai/free/en/shelves/computer-science/) · [Artificial Intelligence · 2 works](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · [Computer Vision and Pattern Recognition · 2 works](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · [Language and Linguistics · 2 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · [Hardware and Architecture · 1 work](https://md.research.elamur.ai/free/en/shelves/computer-science/hardware-and-architecture/) 🧭 Topics 2 Research subjects and languages the work is about.[Efficient models & compression · 1 work](https://md.research.elamur.ai/free/en/topics/efficient-models/) · [GPU & parallel computing · 1 work](https://md.research.elamur.ai/free/en/topics/gpu-parallel-computing/) ## Works by year ### 2020s [**2024** 1 paper](https://md.research.elamur.ai/free/en/authors/xiaoxuan-liu/year/2024/) · [**2023** 1 paper](https://md.research.elamur.ai/free/en/authors/xiaoxuan-liu/year/2023/) ## Papers The most cited first (OpenAlex and our library). 1. **[Online Speculative Decoding](https://md.research.elamur.ai/free/en/papers/liu-2023-online-speculative-decoding/)** *(2023 · 65 citations)* Speculative decoding speeds up LLM inference by having a small draft model propose tokens that a large target model checks in parallel. 2. **[MoE-Lightning: High-Throughput MoE Inference on Memory-constrained GPUs](https://md.research.elamur.ai/free/en/papers/cao-2024-moe-lightning-high-throughput-moe/)** *(2024 · 51 citations)* Mixture-of-Experts LLMs keep per-token compute low but need very large amounts of memory. The expert FFNs of Mixtral 8x22B alone take more than 256 GB. This paper targets offline, throughput-oriented batch inference, such as model evaluation, synthetic data generation and data wrangling, when the GPU cannot hold the… ## All works 4 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them. 1. [**Online Speculative Decoding arXiv:2310.07177**Xiaoxuan Liu, Lanxiang Hu, Peter Bailis, et al.*2023 · 65 citations*](https://md.research.elamur.ai/free/en/papers/liu-2023-online-speculative-decoding/) 2. [**MoE-Lightning: High-Throughput MoE Inference on Memory-constrained GPUs ASPLOS 2025**Shiyi Cao, Shu Liu, Tyler Griggs, et al.*2024 · 51 citations*](https://md.research.elamur.ai/free/en/papers/cao-2024-moe-lightning-high-throughput-moe/) 3. **[Mélange: Cost Efficient Large Language Model Serving by Exploiting GPU Heterogeneity ↗](https://arxiv.org/abs/2404.14527) arXiv:2404.14527 · no summary yet**Tyler Griggs et al.*2024 · 26 citations* 4. **[TurboSpec: Closed-loop Speculation Control System for Optimizing LLM Serving Goodput ↗](https://arxiv.org/abs/2406.14066) arXiv (Cornell University) · no summary yet**Xiaoxuan Liu et al.*2024 · 20 citations* ## Co-authors here 11 co-authors with a page, the most papers together first. - [Ion Gabriel Stoica](https://md.research.elamur.ai/free/en/authors/ion-gabriel-stoica/) ×2 - [Alvin Cheung](https://md.research.elamur.ai/free/en/authors/alvin-cheung/) - [Hao Zhang](https://md.research.elamur.ai/free/en/authors/hao-zhang/) - [Joseph E. Gonzalez](https://md.research.elamur.ai/free/en/authors/joseph-e-gonzalez/) - [Matei Zaharia](https://md.research.elamur.ai/free/en/authors/matei-zaharia/) - [Peter D. Bailis](https://md.research.elamur.ai/free/en/authors/peter-d-bailis/) - [Shiyi Cao](https://md.research.elamur.ai/free/en/authors/shiyi-cao/) - [Shu Liu](https://md.research.elamur.ai/free/en/authors/shu-liu/) - [Tyler Griggs](https://md.research.elamur.ai/free/en/authors/tyler-griggs/) - [Ying Sheng](https://md.research.elamur.ai/free/en/authors/ying-sheng/) - [Zhijie Deng](https://md.research.elamur.ai/free/en/authors/zhijie-deng/) ## Venues Where their works here were published, the most works first, with the editions of those that have a page. - ASPLOS 2025 ## Cited by Papers of our library cite their works 156 times (of the 149,439 papers whose bibliographies we read); [18 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/xiaoxuan-liu/cited-by/). Updated 3 November 2026