🧑‍🔬 Xuekai Zhu

🏛️ Affiliations

🎓Shanghai Jiao Tong UniversityShanghai · China2023–2026 · 3 paperscurrent🏢China State ShipbuildingBeijing · China2026 · 2 paperscurrent🎓ShanghaiTech UniversityShanghai · China2017–2022 · 13 papers🎓Tsinghua UniversityBeijing · China2023–2025 · 4 papers🏥University Medical Center FreiburgFreiburg im Breisgau · Germany2014–2016 · 3 papers🎓University of FreiburgFreiburg im Breisgau · Germany2014–2016 · 3 papers🏛️Chinese Academy of SciencesBeijing · China2010–2013 · 3 papers🔬Institute of MicrobiologyBeijing · China2010–2013 · 3 papers🎓Zhejiang Sci-Tech UniversityHangzhou · China2023–2024 · 2 papers🔬Deutsches Konsortium für Translationale KrebsforschungHeidelberg · Germany2015–2016 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 4 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. TTRL: Test-Time Reinforcement Learning (2025 · 76 citations)
   Reinforcement learning is now a main way to strengthen reasoning in large language models, but it usually needs labeled answers.
2. MedXpertQA: Benchmarking Expert-Level Medical Reasoning and Understanding (2025 · 65 citations)
   Popular medical QA benchmarks such as MedQA and MMLU (Medical) no longer challenge frontier models. o1-preview reportedly reaches 96% on MedQA-USMLE. Multimodal sets like VQA-Rad or PMC-VQA mostly contain simple caption-derived questions without clinical context. MedXpertQA addresses both gaps. This multiple-choice…
3. Reasoning with Exploration: An Entropy Perspective (2025 · 63 citations)
   RL training of LLMs with verifiable rewards tends to over-exploit. Models settle into narrow strategies, and reasoning gains level off. The authors ask whether token-level entropy, a classic exploration signal in RL, can identify exploratory reasoning. They analyse Qwen2.5-Base-7B on math problems and find that…

All works

6 works of theirs in our library, the most cited first; 3 with a page here, the others link their original until we summarise them.

1. Noninvasive positron emission tomography and fluorescence imaging of CD133 + tumor stem cells ↗Proceedings of the National Academy of Sciences · no summary yetSimone Gaedicke et al.2014 · 98 citations
2. TTRL: Test-Time Reinforcement LearningConference on Neural Information Processing Systems (NeurIPS)Yuxin Zuo, Kaiyan Zhang, Li Sheng, et al.2025 · 76 citations
3. MedXpertQA: Benchmarking Expert-Level Medical Reasoning and UnderstandingarXiv:2501.18362Yuxin Zuo, Shang Qu, Yifei Li, et al.2025 · 65 citations
4. Reasoning with Exploration: An Entropy PerspectivearXiv:2506.14758Daixuan Cheng, Shaohan Huang, Xuekai Zhu, et al.2025 · 63 citations
5. PaD: Program-aided Distillation Can Teach Small Models Reasoning Better than Chain-of-thought Fine-tuning ↗Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) · no summary yetXuekai Zhu et al.2024 · 35 citations
6. StoryTrans: Non-Parallel Story Author-Style Transfer with Discourse Representations and Content Enhancing ↗Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yetXuekai Zhu et al.2023 · 13 citations

🤝 Co-authors here

12 of 19 co-authors with a page, the most papers together first.

• Ermo Hua ×2
• Kaiyan Zhang ×2
• Shang Qu ×2
• Yuxin Zuo ×2
• Biqing Qi
• Bo Dai
• Bowen Zhou
• Daixuan Cheng
• Furu Wei
• Ganqu Cui
• Haozhan Li
• Li Sheng

Venues

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

• Conference on Neural Information Processing Systems (NeurIPS): NeurIPS 2025
• Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
• Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
• Proceedings of the National Academy of Sciences

🔗 Cited by

Papers of our library cite their works 229 times (of the 149,439 papers whose bibliographies we read); 75 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/xuekai-zhu/