--- title: "Ion Gabriel Stoica — author profile and papers in our library" description: "Ion Gabriel Stoica, University of California, Santa Cruz: 13 papers on Elamur Research (2023–2024), h-index 132 — affiliations, topics…" canonical: "https://research.elamur.ai/free/en/authors/ion-gabriel-stoica/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/ion-gabriel-stoica/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Ion Gabriel Stoica # Ion Gabriel Stoica Ion Gabriel Stoica has 13 papers in our library, in 2023–2024, most of them on [Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/), [Evaluation & benchmarks](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/), [Dialogue systems](https://md.research.elamur.ai/free/en/topics/dialogue-systems/); often with [Joseph E. Gonzalez](https://md.research.elamur.ai/free/en/authors/joseph-e-gonzalez/), [Wei-Lin Chiang](https://md.research.elamur.ai/free/en/authors/wei-lin-chiang/), [Lianmin Zheng](https://md.research.elamur.ai/free/en/authors/lianmin-zheng/). 13 papers in our library · 2023–2024 [OpenAlex](https://openalex.org/A5041920173) · [ORCID](https://orcid.org/0000-0002-5373-0088) · [Wikidata](https://www.wikidata.org/wiki/Q130801003) · [**h-index 132**](https://openalex.org/authors/A5041920173) · [717 works](https://openalex.org/works?filter=author.id:A5041920173) · [99,061 citations](https://openalex.org/works?filter=author.id:A5041920173&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [📄 13 works in our library](https://md.research.elamur.ai/free/en/authors/ion-gabriel-stoica/#papers) · [🔗 Cited 8,499 times in our library](https://md.research.elamur.ai/free/en/authors/ion-gabriel-stoica/cited-by/) · [571 more in our library without a page yet](#also) · [⭐ Paper Stars ranking: #468](https://md.research.elamur.ai/free/en/paper-stars/page/5/#star-468) 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=Ion+Gabriel+Stoica) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Ion+Gabriel+Stoica) · [dblp](https://dblp.org/search?q=Ion+Gabriel+Stoica) · [ACL Anthology](https://aclanthology.org/search/?q=Ion+Gabriel+Stoica) ## Affiliations [🎓**University of California, Berkeley** Berkeley · United States 2000–2026 · 442 papersEmployment since 2000 · Professor, Electrical Engineering and Computer Science*current*](https://md.research.elamur.ai/free/en/universities/university-of-california-berkeley/) · [🏢**Orano** Washington D.C. · United States 2026 · 1 paper*current*](https://ror.org/04eb8df09) · [🎓**University of California, Santa Cruz** Santa Cruz · United States 2026 · 1 paper*current*](https://md.research.elamur.ai/free/en/universities/university-of-california-santa-cruz/) · [🎓**Carnegie Mellon University** Pittsburgh · United States 1997–2003 · 16 papers](https://md.research.elamur.ai/free/en/universities/carnegie-mellon-university/) · [🎓**Old Dominion University** Norfolk · United States 1994–2002 · 14 papers](https://ror.org/04zjtrb98) · [🏢**Databricks** San Francisco · United States 2014–2018 · 7 papers](https://md.research.elamur.ai/free/en/companies/databricks/) · [🔬**International Computer Science Institute** Berkeley · United States 2003–2024 · 4 papers](https://md.research.elamur.ai/free/en/labs/international-computer-science-institute/) · [🔬**Central University Library** Bucharest · Romania 1992–1995 · 4 papers](https://ror.org/05qhw9x92) · [🎓**Stanford University** Stanford · United States 2024 · 2 papers](https://md.research.elamur.ai/free/en/universities/stanford-university/) · [🎓**Berkeley College** New York · United States 2017–2019 · 2 papers](https://ror.org/02xewxa75) From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 18 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 12 The field of science this work belongs to (OpenAlex fields).[Computer Science · 13 works](https://md.research.elamur.ai/free/en/shelves/computer-science/) · [Arts and Humanities · 12 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · [Artificial Intelligence · 13 works](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · [Language and Linguistics · 12 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · [Hardware and Architecture · 3 works](https://md.research.elamur.ai/free/en/shelves/computer-science/hardware-and-architecture/) · [Information Systems · 4 works](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · [Computer Vision and Pattern Recognition · 3 works](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · [Computer Networks and Communications · 1 work](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-networks-and-communications/) · [Computer Science Applications · 1 work](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-science-applications/) · [Safety Research · 1 work](https://md.research.elamur.ai/free/en/shelves/social-sciences/safety-research/) · [Social Sciences · 1 work](https://md.research.elamur.ai/free/en/shelves/social-sciences/) · [Mathematics · 1 work](https://md.research.elamur.ai/free/en/shelves/mathematics/) 🧭 Topics 5 Research subjects and languages the work is about.[Language models & pretraining · 10 works](https://md.research.elamur.ai/free/en/topics/language-models/) · [Efficient models & compression · 2 works](https://md.research.elamur.ai/free/en/topics/efficient-models/) · [Evaluation & benchmarks · 5 works](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/) · [Dialogue systems · 1 work](https://md.research.elamur.ai/free/en/topics/dialogue-systems/) · [Bias, fairness & safety · 1 work](https://md.research.elamur.ai/free/en/topics/bias-fairness-safety/) 💡 Concepts 4 Key ideas and methods explained on our concept pages.[Language model · 1 work](https://md.research.elamur.ai/free/en/concepts/language-model/) · [Large language models · 1 work](https://md.research.elamur.ai/free/en/concepts/large-language-models/) · [Retrieval-augmented generation · 1 work](https://md.research.elamur.ai/free/en/concepts/retrieval-augmented-generation/) · [Chatbots · 1 work](https://md.research.elamur.ai/free/en/concepts/chatbot/) ## Works by year ### 2020s [**2024** 8 papers](https://md.research.elamur.ai/free/en/authors/ion-gabriel-stoica/year/2024/) · [**2023** 5 papers](https://md.research.elamur.ai/free/en/authors/ion-gabriel-stoica/year/2023/) ## Papers The most cited first (OpenAlex and our library). 1. **[Efficient Memory Management for Large Language Model Serving with PagedAttention](https://md.research.elamur.ai/free/en/papers/kwon-2023-efficient-memory-management-large-language/)** *(2023 · 4,531 citations)* Serving large language models efficiently depends on how many requests a GPU can process together. The limiting factor is often the KV cache: the stored attention keys and values for each request, whose size changes as tokens are generated and whose final length is unknown in advance. Earlier systems such as… 2. **[SGLang: Efficient Execution of Structured Language Model Programs](https://md.research.elamur.ai/free/en/papers/zheng-2023-sglang-efficient-execution-structured-language/)** *(2023 · 729 citations)* Modern LLM applications such as agents, few-shot evaluation, tree-of-thought search, RAG and JSON extraction rarely make a single model call. 3. **[LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://md.research.elamur.ai/free/en/papers/jain-2024-livecodebench-holistic-contamination-free-evaluation/)** *(2024 · 578 citations)* Widely used code benchmarks such as HumanEval and MBPP have become saturated. They also risk leaking into training data, and they test only one skill: turning a natural-language description into code. LiveCodeBench addresses these problems with a benchmark that keeps growing. It collects fresh problems from weekly… 4. **[Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference](https://md.research.elamur.ai/free/en/papers/chiang-2024-chatbot-arena-open-platform-evaluating/)** *(2024 · 546 citations)* The authors show that conventional LLM benchmarks poorly reflect how models are actually used. These are fixed sets of closed-ended questions with reference answers: over time they leak into training data, become saturated, and do not account for human preferences in open-ended tasks. As an alternative, they propose… 5. **[LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset](https://md.research.elamur.ai/free/en/papers/zheng-2023-lmsys-chat-1m-large-scale/)** *(2023 · 242 citations)* Research into how people use large language models has been held back by the lack of public logs of genuine user interactions. 6. **[From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline](https://md.research.elamur.ai/free/en/papers/li-2024-crowdsourced-data-high-quality-benchmarks/)** *(2024 · 210 citations)* Static LLM benchmarks saturate quickly, can leak into training data, and mostly test close-ended tasks. Expert-built sets are expensive: GPQA's 500 questions reportedly cost over $120,000. Live human evaluation such as Chatbot Arena is too slow for developers to use routinely. The authors present BenchBuilder, an… 7. **[RAFT: Adapting Language Model to Domain Specific RAG](https://md.research.elamur.ai/free/en/papers/zhang-2024-raft-adapting-language-model-domain/)** *(2024 · 137 citations)* The paper asks how a pretrained LLM should be prepared when it will answer questions over a known, fixed document collection, such as enterprise files, medical literature or API documentation, with retrieval at inference time. 8. **[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/)** *(2024 · 114 citations)* Generating text with LLMs one token at a time is slow. Each step is limited by memory bandwidth, so most of the GPU's compute sits idle. Speculative decoding helps, but it needs a draft model, which is hard to train and often fails to transfer across base models or datasets. The authors propose Lookahead Decoding… 9. **[RouteLLM: Learning to Route LLMs with Preference Data](https://md.research.elamur.ai/free/en/papers/ong-2024-routellm-learning-route-llms-preference/)** *(2024 · 109 citations)* Deploying LLMs forces a trade-off: frontier models such as GPT-4 give the best answers but are costly, while cheaper models like Mixtral-8x7B struggle with harder requests. 10. **[Rethinking Benchmark and Contamination for Language Models with Rephrased Samples](https://md.research.elamur.ai/free/en/papers/yang-2023-rethinking-benchmark-contamination-language-models/)** *(2023 · 103 citations)* Public LLM benchmarks can leak into training corpora. Standard decontamination looks for surface similarity, using either n-gram overlap or an embedding-similarity threshold. The authors show that these checks are easy to get around. They had GPT-4 reword test items, or rewrite code in a different style or… 11. **[JudgeBench: A Benchmark for Evaluating LLM-based Judges](https://md.research.elamur.ai/free/en/papers/tan-2024-judgebench-benchmark-evaluating-llm-based/)** *(2024 · 101 citations)* LLM-based judges are now widely used to rank models, act as reward models, and pick the best candidate answers, yet their own reliability is seldom tested. 12. **[OR-Bench: An Over-Refusal Benchmark for Large Language Models](https://md.research.elamur.ai/free/en/papers/cui-2024-bench-over-refusal-benchmark-large/)** *(2024 · 76 citations)* Safety-tuned LLMs often refuse harmless requests that merely look risky. Before this work, the problem had no large-scale way to be measured. The only dedicated test set, XSTest, has 250 hand-written prompts, and recent strong models now answer almost all of them. The authors build an automated pipeline to fill this… 13. **[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. ## All works 584 works of theirs in our library, the most cited first; 13 with a page here, the others link their original until we summarise them. 1. **[Chord ↗](https://doi.org/10.1145/383059.383071) ACM SIGCOMM Conference on Applications, Technologies, Architectures, and Protocols for Computer Communications (SIGCOMM) · no summary yet**Ion Gabriel Stoica et al.*2001 · 9,623 citations* 2. **[Above the Clouds: A Berkeley View of Cloud Computing ↗](https://openalex.org/W2131629857) no summary yet**Michael Armbrust et al.*2009 · 5,696 citations* 3. [**Efficient Memory Management for Large Language Model Serving with PagedAttention arXiv:2309.06180**Woosuk Kwon, Zhuohan Li, Siyuan Zhuang, et al.*2023 · 4,531 citations*](https://md.research.elamur.ai/free/en/papers/kwon-2023-efficient-memory-management-large-language/) 4. **[Spark: cluster computing with working sets ↗](https://openalex.org/W2189465200) no summary yet**Matei Zaharia et al.*2010 · 4,118 citations* 5. **[Resilient distributed datasets: a fault-tolerant abstraction for in-memory cluster computing ↗](https://openalex.org/W2131975293) no summary yet**Matei Zaharia et al.*2012 · 3,546 citations* 6. **[Chord: a scalable peer-to-peer lookup protocol for internet applications ↗](https://doi.org/10.1109/tnet.2002.808407) IEEE/ACM Transactions on Networking · no summary yet**Ion Gabriel Stoica et al.*2002 · 3,135 citations* 7. **[Apache Spark ↗](https://doi.org/10.1145/2934664) Communications of the ACM · no summary yet**Matei Zaharia et al.*2016 · 2,436 citations* 8. **[Chord ↗](https://doi.org/10.1145/964723.383071) ACM SIGCOMM Computer Communication Review · no summary yet**Ion Gabriel Stoica et al.*2001 · 1,923 citations* 9. **[Improving MapReduce performance in heterogeneous environments ↗](https://doi.org/10.5555/1855741.1855744) no summary yet**Matei Zaharia et al.*2008 · 1,592 citations* 10. **[Mesos: a platform for fine-grained resource sharing in the data center ↗](https://doi.org/10.5555/1972457.1972488) no summary yet**Benjamin Hindman et al.*2011 · 1,582 citations* 11. **[Wide-area cooperative storage with CFS ↗](https://doi.org/10.1145/502034.502054) no summary yet**Frank Dabek et al.*2001 · 1,430 citations* 12. **[Delay scheduling ↗](https://doi.org/10.1145/1755913.1755940) European Conference on Computer Systems · no summary yet**Matei Zaharia et al.*2010 · 1,395 citations* 13. **[A data-oriented (and beyond) network architecture ↗](https://doi.org/10.1145/1282380.1282402) ACM SIGCOMM Conference on Applications, Technologies, Architectures, and Protocols for Computer Communications (SIGCOMM) · no summary yet**Teemu Koponen et al.*2007 · 1,368 citations* 14. **[Dominant resource fairness: fair allocation of multiple resource types ↗](https://doi.org/10.5555/1972457.1972490) no summary yet**Ali Ghodsi et al.*2011 · 1,077 citations* 15. **[Geographic routing without location information ↗](https://doi.org/10.1145/938985.938996) Proceedings of the 28th Annual International Conference on Mobile Computing And Networking · no summary yet**Ananth Rao et al.*2003 · 748 citations* 16. **[SGLang: Efficient Execution of Structured Language Model Programs](https://md.research.elamur.ai/free/en/papers/zheng-2023-sglang-efficient-execution-structured-language/) [Conference on Neural Information Processing Systems (NeurIPS)](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/)**Lianmin Zheng, Liangsheng Yin, Zhiqiang Xie, et al.*2023 · 729 citations* 17. **[BlinkDB ↗](https://doi.org/10.1145/2465351.2465355) no summary yet**Sameer Agarwal et al.*2013 · 694 citations* 18. **[Understanding the impact of video quality on user engagement ↗](https://doi.org/10.1145/2018436.2018478) ACM SIGCOMM Conference (SIGCOMM) · no summary yet**Florin Dobrian et al.*2011 · 674 citations* 19. **[Internet indirection infrastructure ↗](https://doi.org/10.1145/633025.633033) ACM SIGCOMM Conference on Applications, Technologies, Architectures, and Protocols for Computer Communications (SIGCOMM) · no summary yet**Ion Gabriel Stoica et al.*2002 · 642 citations* 20. **[Tune: A Research Platform for Distributed Model Selection and Training ↗](https://arxiv.org/abs/1807.05118) arXiv (Cornell University) · no summary yet**Richard Liaw et al.*2018 · 640 citations* 21. **[Reining in the outliers in map-reduce clusters using Mantri ↗](https://doi.org/10.5555/1924943.1924962) Operating Systems Design and Implementation · no summary yet**Ganesh Ananthanarayanan et al.*2010 · 639 citations* 22. **[GraphX ↗](https://doi.org/10.1145/2484425.2484427) no summary yet**Reynold Xin et al.*2013 · 581 citations* 23. [**LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code arXiv:2403.07974**Naman Jain, King Han, Alex Gu, et al.*2024 · 578 citations*](https://md.research.elamur.ai/free/en/papers/jain-2024-livecodebench-holistic-contamination-free-evaluation/) 24. **[The impact of DHT routing geometry on resilience and proximity ↗](https://doi.org/10.1145/863955.863998) ACM SIGCOMM Conference on Applications, Technologies, Architectures, and Protocols for Computer Communications (SIGCOMM) · no summary yet**Krishna P. Gummadi et al.*2003 · 567 citations* 25. **[Robust incentive techniques for peer-to-peer networks ↗](https://doi.org/10.1145/988772.988788) ACM Conference on Electronic Commerce (EC) · no summary yet**Michal Feldman et al.*2004 · 558 citations* [See all 584 works by Ion Gabriel Stoica →](https://md.research.elamur.ai/free/en/authors/ion-gabriel-stoica/works/) ## Co-authors here 12 of 41 co-authors with a page, the most papers together first. - [Joseph E. Gonzalez](https://md.research.elamur.ai/free/en/authors/joseph-e-gonzalez/) ×8 - [Wei-Lin Chiang](https://md.research.elamur.ai/free/en/authors/wei-lin-chiang/) ×6 - [Lianmin Zheng](https://md.research.elamur.ai/free/en/authors/lianmin-zheng/) ×5 - [Hao Zhang](https://md.research.elamur.ai/free/en/authors/hao-zhang/) ×4 - [Ying Sheng](https://md.research.elamur.ai/free/en/authors/ying-sheng/) ×4 - [Siyuan Zhuang](https://md.research.elamur.ai/free/en/authors/siyuan-zhuang/) ×3 - [Tianle Li](https://md.research.elamur.ai/free/en/authors/tianle-li/) ×3 - [Banghua Zhu](https://md.research.elamur.ai/free/en/authors/banghua-zhu/) ×2 - [Cody Hao Yu](https://md.research.elamur.ai/free/en/authors/cody-hao-yu/) ×2 - [Naman Jain](https://md.research.elamur.ai/free/en/authors/naman-jain/) ×2 - [Peter D. Bailis](https://md.research.elamur.ai/free/en/authors/peter-d-bailis/) ×2 - [Tianhao Wu](https://md.research.elamur.ai/free/en/authors/tianhao-wu/) ×2 ## Venues Where their works here were published, the most works first, with the editions of those that have a page. - Lecture notes in computer science ×26 - PubMed ×26 - Proceedings of the VLDB Endowment ×18 - ACM SIGCOMM Computer Communication Review ×14 - Proceedings - ACM-SIGMOD International Conference on Management of Data ×12 - Networked Systems Design and Implementation ×11 - neural information processing systems ×11 - ACM SIGCOMM Conference on Applications, Technologies, Architectures, and Protocols for Computer Communications (SIGCOMM) ×8 - UC Berkeley ×8 - ACM Symposium on Cloud Computing (SoCC) ×5 - ACM Workshop on Hot Topics in Networks (HotNets) ×5 - IEEE/ACM Transactions on Networking ×5 ## Cited by Papers of our library cite their works 8,499 times (of the 149,439 papers whose bibliographies we read); [1,081 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/ion-gabriel-stoica/cited-by/). Updated 2 November 2026