🧑‍🔬 Xingyu Zhang

🏛️ Affiliations

🎓University of PittsburghPittsburgh · United States2021–2026 · 36 paperscurrent🏥University of Pittsburgh Medical CenterPittsburgh · United States2021–2026 · 22 paperscurrent🔬PLA Academy of Military ScienceBeijing · China2023–2026 · 8 paperscurrent🏥Tianjin Medical University General HospitalTianjin · China2024–2026 · 7 paperscurrent🎓Tianjin Medical UniversityTianjin · China2024–2026 · 6 paperscurrent🎓Sichuan UniversityChengdu · China2010–2026 · 3 papersEducation 2010–2013current🎓University of Chinese Academy of SciencesBeijing · China2024–2026 · 3 paperscurrent🏥Third People's Hospital of HefeiHefei · China2026 · 1 papercurrent🏥West China Medical Center of Sichuan UniversityChengdu · China2026 · 1 papercurrent🎓University of MichiganAnn Arbor · United States2010–2022 · 44 papersEmployment since 2018

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 49 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. Igniting Creative Writing in Small Language Models: LLM-as-a-Judge versus Multi-Agent Refined Rewards (2025 · 10 citations)
   Large LLMs write creative text well but are costly to serve at high request volumes. The authors therefore ask how a compact model can reach similar creativity without expensive human preference labels. In an RLAIF setup, they train Qwen2.5 7B with GRPO to write Chinese greetings and compare two sources of AI reward.
2. UniCreative: Unifying Long-form Logic and Short-form Sparkle via Reference-Free Reinforcement Learning (2026 · 1 citation)
   LLM creative writing faces two opposite problems. Long stories and scripts need global planning, or they drift off topic, repeat themselves and lose structure. Short pieces such as poems, slogans or blessings get worse when forced through rigid outlines, and models already tend toward bland, high-probability wording.…

🤝 Co-authors here

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

• Long Xia ×2
• Xiaolong Wei ×2
• Zhejun Zhao ×2
• Daiting Shi
• Dawei Yin
• Peiying Yu
• Simin Niu
• Yuchen Li

Venues

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

• 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 10 times (of the 149,439 papers whose bibliographies we read); 4 citing papers with a page here →.

Updated 1 November 2026

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