🧑‍🔬 Jinman Zhao

🏛️ Affiliations

🎓University of TorontoToronto · Canada2021–2026 · 13 paperscurrent🎓University of Wisconsin–MadisonMadison · United States2015–2021 · 7 papers🎓Hebei University of Science and TechnologyShijiazhuang · China2023–2024 · 4 papers🏢AmazonSeattle · United States2023–2024 · 3 papers🎓Hebei Agricultural UniversityBaoding · China2022 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 2 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. LongRecipe: Recipe for Efficient Long Context Generalization in Large Language Models (2025 · 16 citations)
   Large language models handle inputs poorly once these exceed the context length seen during pretraining. Continuing training on full-length sequences fixes this but is expensive, since attention cost grows quadratically with length. LongRecipe is a training framework that extends the context window without training…
2. UORA: Uniform Orthogonal Reinitialization Adaptation in Parameter Efficient Fine-Tuning of Large Models (2025 · 14 citations)
   Fully fine-tuning large models is expensive in compute and in storage for per-task checkpoints. LoRA lowers this cost by training low-rank matrices. VeRA goes further: it freezes random projection matrices and trains only two scaling vectors, but it needs a high rank to stay competitive, which raises computation. The…
3. Role-Play Paradox in Large Language Models: Reasoning Performance Gains and Ethical Dilemmas (2024 · 9 citations)
   Role-play prompting, where an LLM is told to act as a teacher, scriptwriter, or even an object like a coin, is known to improve reasoning.
4. Tiny Budgets, Big Gains: Parameter Placement Strategy in Parameter Super-Efficient Fine-Tuning (2025 · 8 citations)
   Parameter-efficient fine-tuning methods such as LoRA lower the cost of adapting large models. Yet models now reach hundreds of billions of parameters, so even rank-1 LoRA can be too heavy for mobile hardware or labs with little compute. The authors ask how a very small, fixed budget of trainable parameters should be…
5. CodeHacker: Automated Test Case Generation for Detecting Vulnerabilities in Competitive Programming Solutions (2026 · 7 citations)
   Code benchmarks for LLMs often have test suites that miss subtle corner cases, so flawed programs are wrongly marked correct.
6. On the Representation Geometry of LoRA Model Merging (2026)
   Combining several task-specific LoRA adapters into one model without further training is hard because their low-rank updates tend to occupy misaligned subspaces.

🤝 Co-authors here

12 of 20 co-authors with a page, the most papers together first.

• Yining Wang ×3
• Jiaru Li ×2
• Linbo Cao ×2
• Xueyan Zhang ×2
• Yulan Hu ×2
• Anh Tuan Luu
• Bryan Hooi
• Chenyang Lu
• Erxue Min
• Gerald Penn
• Jing Huang
• Qing Gu

Venues

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

• Annual Meeting of the Association for Computational Linguistics (ACL) ×3: ACL 2026, ACL 2025 ×2
• Conference on Empirical Methods in Natural Language Processing (EMNLP): EMNLP 2025
• Findings of the Association for Computational Linguistics: Findings of the Association for Computational Linguistics 2026

🔗 Cited by

Papers of our library cite their works 48 times (of the 149,439 papers whose bibliographies we read); 14 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/jinman-zhao/