Elamur Research⌕
☰
home / authors / Zinan Lin

Zinan Lin

Zinan Lin has 2 papers in our library, in 2021–2023, most of them on Language models & pretraining; often with Eugene Brevdo, Krzysztof Choromanski, Xuefei Ning.

2 papers in our library · 2021–2023

OpenAlex · ORCID · h-index 14 · 62 works · 1,250 citations OpenAlex, 2026-10-14

📄 2 works in our library · 🔗 Cited 90 times in our library · 3 more in our library without a page yet · ⭐ Paper Stars ranking: #8096

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: Google Scholar · Semantic Scholar · dblp · ACL Anthology

 Affiliations

🏢MicrosoftRedmond · United States2023–2026 · 16 paperscurrent🏢InterDigitalWilmington · United States2009–2026 · 8 paperscurrent🎓Carnegie Mellon UniversityPittsburgh · United States2017–2023 · 13 papersEducation 2017–2023 · PhD, Electrical and Computer Engineering
🏛️Microsoft ResearchRedmond · United States2022Employment since 2022 · Principal Researcher, Algorithms Group
🎓Tsinghua UniversityBeijing · China2013–2017Education 2013–2017 · Bachelor of Engineering, Electronic Engineering

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 1 more institution on single bylines are not listed.

 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📚 Shelves 6The field of science this work belongs to (OpenAlex fields).Computer Science · 2 worksArtificial Intelligence · 2 worksInformation Systems · 2 worksArts and Humanities · 1 workLanguage and Linguistics · 1 workHardware and Architecture · 1 work

🧭 Topics 1Research subjects and languages the work is about.Language models & pretraining · 1 work

 Works by year

2020s

20231 paper20211 paper

 Papers

The most cited first (OpenAlex and our library).

  1. Skeleton-of-Thought: Prompting LLMs for Efficient Parallel Generation (2023 · 72 citations)
    Answer generation in LLMs is slow largely because tokens are produced strictly one after another. This work tackles that bottleneck without modifying models, serving systems or hardware. Skeleton-of-Thought (SoT) is a two-stage prompting scheme inspired by how people outline before writing. First, the LLM drafts a…
  2. MLGO: a Machine Learning Guided Compiler Optimizations Framework (2021 · 42 citations)
    Academic research has repeatedly shown that machine learning can outperform hand-written compiler heuristics, yet production-grade compilers had not adopted it.

All works

5 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. Skeleton-of-Thought: Prompting LLMs for Efficient Parallel GenerationarXiv:2307.15337Xuefei Ning, Zinan Lin, Zixuan Zhou, et al.2023 · 72 citations
  2. MLGO: a Machine Learning Guided Compiler Optimizations FrameworkarXiv:2101.04808Mircea Trofin, Yundi Qian, Eugene Brevdo, et al.2021 · 42 citations
  3. RedCode: Risky Code Execution and Generation Benchmark for Code Agents ↗neural information processing systems · no summary yetChengquan Guo et al.2024 · 27 citations
  4. MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation Models ↗arXiv (Cornell University) · no summary yetChejian Xu et al.2025 · 5 citations
  5. RedCodeAgent: Automatic Red-teaming Agent against Diverse Code Agents ↗arXiv (Cornell University) · no summary yetChengquan Guo et al.2025

 Co-authors here

5 co-authors with a page, the most papers together first.

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

 Cited by

Papers of our library cite their works 90 times (of the 149,439 papers whose bibliographies we read); 26 citing papers with a page here →.

Updated

This page in Markdown → https://md.research.elamur.ai/free/en/authors/zinan-lin/