🧑‍🔬 Yanzhe Zhang

🏛️ Affiliations

🎓Jilin UniversityChangchun · China2015–2026 · 32 paperscurrent🎓Georgia Institute of TechnologyAtlanta · United States2022–2026 · 7 paperscurrent🎓Westlake UniversityHangzhou · China2025–2026 · 4 paperscurrent🎓Zhejiang UniversityHangzhou · China2021–2026 · 3 paperscurrent🎓Liaoning UniversityShenyang · China2026 · 1 papercurrent🏛️Ministry of Agriculture and Rural AffairsBeijing · China2026 · 1 papercurrent🎓Zhejiang A & F UniversityLin’an Shi · China2026 · 1 papercurrent🎓Jiangsu UniversityZhenjiang · China2023–2024 · 3 papers🎓University of Science and Technology BeijingBeijing · China2022–2024 · 3 papers🎓Shijiazhuang Tiedao UniversityShijiazhuang · China2022–2023 · 3 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 13 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. Best Practices and Lessons Learned on Synthetic Data (2024 · 119 citations)
   Strong AI systems need large, varied and clean datasets, but such data is often scarce, expensive to label, or restricted by privacy rules.
2. A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration (2023 · 114 citations)
   Multi-agent systems built on large language models usually rely on a fixed set of agents and a communication pattern that is designed in advance.
3. LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding (2023 · 98 citations)
   Visual instruction-tuned assistants such as LLaVA learn mostly from natural photos, so they handle text inside images poorly.
4. Design2Code: Benchmarking Multimodal Code Generation for Automated Front-End Engineering (2025 · 37 citations)
   The paper asks how well multimodal large language models (MLLMs) can turn a webpage screenshot into HTML/CSS code that renders the same page.
5. Attacking Vision-Language Computer Agents via Pop-ups (2025 · 32 citations)
   The paper examines a simple but overlooked risk for computer-use agents built on vision-language models (VLMs): visible adversarial pop-ups that an experienced person would dismiss.
6. Distilling an End-to-End Voice Assistant Without Instruction Training Data (2025 · 18 citations)
   End-to-end Speech LLMs are usually built with supervised finetuning on speech instruction data. That data is scarce, often recorded by few speakers, and the resulting models tend to lose abilities inherited from their text-only backbone. The authors propose the Distilled Voice Assistant (DiVA), which needs no…
7. SpeechLLM-as-Judges: Towards General and Interpretable Speech Quality Evaluation (2026 · 3 citations)
   Judging how good synthetic speech sounds is still difficult. Common tools such as MOS ratings, A/B tests, or MCD produce a single number or a binary choice, which explains nothing about the judgment. Learned predictors such as UTMOS are usually limited to one task and one language. The authors propose…

All works

14 works of theirs in our library, the most cited first; 7 with a page here, the others link their original until we summarise them.

1. Best Practices and Lessons Learned on Synthetic DataarXiv:2404.07503Ruibo Liu, Jerry Wei, Fangyu Liu, et al.2024 · 119 citations
2. A Dynamic LLM-Powered Agent Network for Task-Oriented Agent CollaborationarXiv:2310.02170Zijun Liu, Yanzhe Zhang, Peng Li, et al.2023 · 114 citations
3. Continual Learning for Text Classification with Information Disentanglement Based Regularization ↗Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · no summary yetYufan Huang et al.2021 · 110 citations
4. LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image UnderstandingarXiv:2306.17107Yanzhe Zhang, Ruiyi Zhang, Jiuxiang Gu, et al.2023 · 98 citations
5. Continual Sequence Generation with Adaptive Compositional Modules ↗Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yetYanzhe Zhang, Xuezhi Wang, Diyi Yang2022 · 43 citations
6. Bounding the Capabilities of Large Language Models in Open Text Generation with Prompt Constraints ↗Findings of the Association for Computational Linguistics: EACL 2023 · no summary yetAlbert Lu et al.2023 · 41 citations
7. Design2Code: Benchmarking Multimodal Code Generation for Automated Front-End EngineeringConference of the North American Chapter of the Association for Computational Linguistics (NAACL)Chenglei Si, Yanzhe Zhang, Ryan Li, et al.2025 · 37 citations
8. Attacking Vision-Language Computer Agents via Pop-upsAnnual Meeting of the Association for Computational Linguistics (ACL)Yanzhe Zhang, Tao Yu, Diyi Yang2025 · 32 citations
9. Distilling an End-to-End Voice Assistant Without Instruction Training DataAnnual Meeting of the Association for Computational Linguistics (ACL)William Held, Yanzhe Zhang, Minzhi Li, et al.2025 · 18 citations
10. Robustness of Demonstration-based Learning Under Limited Data Scenario ↗Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing · no summary yetHongxin Zhang et al.2022 · 18 citations
11. Leveraging Expert Guided Adversarial Augmentation For Improving Generalization in Named Entity Recognition ↗Findings of the Association for Computational Linguistics: ACL 2022 · no summary yetAaron Reich et al.2022 · 9 citations
12. SpeechLLM-as-Judges: Towards General and Interpretable Speech Quality EvaluationAnnual Meeting of the Association for Computational Linguistics (ACL)Hui Wang, Jinghua Zhao, Yifan Yang, et al.2026 · 3 citations
13. Sherpa: Teaching LLMs to Teach Adaptively ↗arXiv (Cornell University) · no summary yetWeixian Xu et al.2026
14. Real-Time Reasoning Agents in Evolving Environments ↗arXiv (Cornell University) · no summary yetWen, Yule et al.2025

🤝 Co-authors here

12 of 33 co-authors with a page, the most papers together first.

• Diyi Yang ×6
• Chenglei Si ×2
• Ruibo Liu ×2
• Andrew M. Dai
• Daiyi Peng
• Denny Zhou
• Fangyu Liu
• Haoqin Sun
• Hui Wang
• Jerry Wei
• Jiaming Zhou
• Jinghua Zhao

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) ×4: ACL 2026, ACL 2025 ×2
• Conference of the North American Chapter of the Association for Computational Linguistics (NAACL): NAACL 2025
• Findings of the Association for Computational Linguistics: ACL 2022
• Findings of the Association for Computational Linguistics: EACL 2023
• Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
• Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

🔗 Cited by

Papers of our library cite their works 421 times (of the 149,439 papers whose bibliographies we read); 130 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/yanzhe-zhang/