🧑‍🔬 Binhang Yuan

🏛️ Affiliations

🎓Hong Kong University of Science and TechnologyHong Kong · China2023–2026 · 47 papersEmployment since 2023 · Assistant Professor, Computer Science and Engineeringcurrent🏢Ant GroupHangzhou · China2026 · 3 paperscurrent🎓Rice UniversityHouston · United States2013–2022 · 22 papersEducation 2013–2020 · PhD, Computer ScienceEmployment 2013–2020 · Ph.D Candidate, Computer Science🎓ETH ZurichZurich · Switzerland2021–2024 · 9 papersEmployment 2021–2023 · Postdoc, Computer Science🎓The Hong Kong University of Science and Technology (Guangzhou)Guangzhou · China2025–2026 · 3 papers🎓Tsinghua UniversityBeijing · China2022–2024 · 3 papers🎓Peking UniversityBeijing · China2025–2026 · 2 papers🎓Fudan UniversityShanghai · China2009–2014 · 2 papersEducation 2009–2013 · Bachelor, Computer Science

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 4 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.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU (2023 · 402 citations)
   Running very large language models usually requires several expensive accelerators. GPT-175B alone needs about 325GB just for its weights. Many workloads, however, are batch jobs where latency matters little, such as benchmarking, information extraction and data wrangling. The authors build FlexGen, an inference…
2. Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time (2023 · 185 citations)
   Serving very large language models is slow, especially when generating tokens one at a time in latency-sensitive settings.
3. AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning (2025 · 80 citations)
   RL training of large reasoning models is slowed down by synchronous system designs. In these designs, generation and training alternate in lockstep, so every batch waits for its longest response, and GPUs sit idle. AReaL is a system that fully separates rollout generation from model updates and runs them on separate…

All works

6 works of theirs in our library, the most cited first; 3 with a page here, the others link their original until we summarise them.

1. Holistic Evaluation of Language Models ↗arXiv:2211.09110 · Published in Transactions on Machine Learning Research (TMLR), 2023 · no summary yetPercy Liang et al.2022 · 1,001 citations
2. FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPUarXiv:2303.06865Ying Sheng, Lianmin Zheng, Binhang Yuan, et al.2023 · 402 citations
3. Deja Vu: Contextual Sparsity for Efficient LLMs at Inference TimeInternational Conference on Machine Learning (ICML)Zichang Liu, Jue Wang, Tri Dao, et al.2023 · 185 citations
4. AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language ReasoningConference on Neural Information Processing Systems (NeurIPS)Wei Fu, Jiaxuan Gao, Xujie Shen, et al.2025 · 80 citations
5. Decentralized Training of Foundation Models in Heterogeneous Environments ↗arXiv:2206.01288 · no summary yetBinhang Yuan et al.2022 · 59 citations
6. CocktailSGD: Fine-tuning Foundation Models over 500Mbps Networks ↗Rare & Special e-Zone (The Hong Kong University of Science and Technology) · no summary yetBeidi Chen et al.2023 · 14 citations

🤝 Co-authors here

12 of 18 co-authors with a page, the most papers together first.

• Christopher Ré ×2
• Beidi Chen
• Ce Zhang
• Chen Zhu
• Clark Barrett
• Daniel Y. Fu
• Joseph E. Gonzalez
• Jue Wang
• Lianmin Zheng
• Max Ryabinin
• Percy Liang
• Tianyi Zhou

Venues

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

• International Conference on Machine Learning (ICML): ICML 2023
• Conference on Neural Information Processing Systems (NeurIPS): NeurIPS 2025
• Rare & Special e-Zone (The Hong Kong University of Science and Technology)

🔗 Cited by

Papers of our library cite their works 1,524 times (of the 149,439 papers whose bibliographies we read); 316 citing papers with a page here →.

Updated 2 November 2026

↑ back to top

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