🧑‍🔬 Hai Li

🏛️ Affiliations

🎓Duke UniversityDurham · United States2017–2026 · 236 papersEmployment 2017–2024 · Clare Boothe Luce Professor, Electrical and Computer Engineering DepartmentEmployment since 2024 · Marie Foote Reel E’46 Distinguished Professor, Electrical and Computer Engineeringcurrent🏢Guangdong Power Grid CompanyGuangzhou · China2023–2026 · 9 paperscurrent🎓University of FloridaGainesville · United States2026 · 1 papercurrent🎓University of PittsburghPittsburgh · United States2011–2018 · 120 papersEmployment 2012–2016 · Associate Professor, Dept. of Electrical and Computer Engineering🎓New York UniversityNew York · United States2009–2013 · 53 papers🎓Civil Aviation University of ChinaTianjin · China2010–2025 · 21 papers🎓Southwest Jiaotong UniversityChengdu · China2019–2024 · 12 papers🎓Purdue University West LafayetteWest Lafayette · United States2000–2006 · 11 papersEducation 2000–2004🎓South China University of TechnologyGuangzhou · China2017–2023 · 9 papers🏢SeagateCupertino · United States2007–2010 · 9 papersEmployment 2007–2009

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 71 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

2010s

📄 Papers

The most cited first (OpenAlex and our library).

1. Learning Structured Sparsity in Deep Neural Networks (2016 · 530 citations)
   Sparsifying a deep network weight by weight shrinks its parameter count, but the zeros end up scattered across memory.
2. FLAT-LLM: Fine-grained Low-rank Activation Space Transformation for Large Language Model Compression (2026 · 2 citations)
   Large language models are costly to run on limited hardware. Low-rank compression helps, but SVD-based variants often lose accuracy, need recovery fine-tuning, and split layers into two smaller matrix multiplications that run poorly on GPUs. SliceGPT avoids SVD but adds adapters on residual paths, which costs memory.…

All works

3 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. Learning Structured Sparsity in Deep Neural NetworksarXiv:1608.03665Wei Wen, Chunpeng Wu, Yandan Wang, et al.2016 · 530 citations
2. Feature Space Perturbations Yield More Transferable Adversarial Examples ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetNathan Inkawhich et al.2019 · 176 citations
3. FLAT-LLM: Fine-grained Low-rank Activation Space Transformation for Large Language Model CompressionFindings of the Association for Computational LinguisticsJiayi Tian, Ryan Solgi, Jinming Lu, et al.2026 · 2 citations

🤝 Co-authors here

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

• Wei Wen
• Yifan Yang
• Yiran Chen
• Zheng Zhang

Venues

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

• Findings of the Association for Computational Linguistics: Findings of the Association for Computational Linguistics 2026
• IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings

🔗 Cited by

Papers of our library cite their works 129 times (of the 149,439 papers whose bibliographies we read); 8 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/hai-li/