🧑‍🔬 Xiaowen Chu

🏛️ Affiliations

🎓The Hong Kong University of Science and Technology (Guangzhou)Guangzhou · China2021–2026 · 130 papersEmployment since 2021 · Professor, Data Science and Analyticscurrent🎓Hong Kong University of Science and TechnologyHong Kong · China1999–2026 · 49 papersEducation 1999–2003 · PhD, Computer ScienceEmployment · Affiliate Professor, Computer Science and Engineeringcurrent🎓University of Hong KongPok Fu Lam · China2012–2026 · 5 paperscurrent🔬Guangzhou HKUST Fok Ying Tung Research InstituteGuangzhou · China2026 · 2 paperscurrent🎓South China University of TechnologyGuangzhou · China2026 · 2 paperscurrent🎓Hong Kong Baptist UniversityHong Kong · China2003–2023 · 215 papers🎓Tsinghua UniversityBeijing · China1994–1999Education 1994–1999 · Bachemor, Computer Science

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 12 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. LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning (2023 · 58 citations)
   Full-parameter fine-tuning of large language models needs enormous GPU memory. LoRA is the common cheaper option, but it often falls short of Full-FT because its updates are restricted to a low-rank gradient. The authors argue that LoRA's two factors contribute unequally. The product of the projection-down matrix A…
2. Probing the Plasticity and Correlation of LLM Value Systems: LLM Value Rankings are Not Stable (2026)
   Earlier work found that different LLMs rank their values in similar ways. This paper asks whether those rankings stay fixed when the model is pushed by its context, and whether some values tend to shift together. The authors build on the LITMUSVALUES setup. Models face two-action dilemmas, each action tied to one of…

All works

6 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. Highly Scalable Deep Learning Training System with Mixed-Precision: Training ImageNet in Four Minutes ↗arXiv:1807.11205 · no summary yetXianyan Jia et al.2018 · 348 citations
2. LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuningarXiv:2308.03303Longteng Zhang, Lin Zhang, Shaohuai Shi, et al.2023 · 58 citations
3. Structured Scaling of AI Discovery Across Diverse Scientific Domains ↗arXiv (Cornell University) · no summary yetHaotian Ye et al.2026 · 7 citations
4. DiffAdapt: Difficulty-Adaptive Reasoning for Token-Efficient LLM Inference ↗arXiv (Cornell University) · no summary yetXiang Liu et al.2025 · 2 citations
5. Are Dilemmas and Conflicts in LLM Alignment Solvable? A View from Priority Graph ↗arXiv (Cornell University) · no summary yetZhenheng Tang et al.2026 · 1 citation
6. Probing the Plasticity and Correlation of LLM Value Systems: LLM Value Rankings are Not StableFindings of the Association for Computational LinguisticsZhenheng Tang, Qihua Pan, Jingya Shen, et al.2026

🤝 Co-authors here

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

• Bo Li ×2
• Lin Zhang
• Qian Wang
• Xiang Liu

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

🔗 Cited by

Papers of our library cite their works 124 times (of the 149,439 papers whose bibliographies we read); 8 citing papers with a page here →.

Updated 1 November 2026

↑ back to top

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