🧑‍🔬 Wei Xia

🏛️ Affiliations

🎓Fudan UniversityShanghai · China2021–2026 · 2 paperscurrent🏢Huawei TechnologiesShenzhen · China2024–2025 · 3 papers🏢GoogleMountain View · United States2021–2024 · 3 papers🎓Harbin Medical UniversityHarbin · China2023–2024 · 3 papers🎓Tianjin University of Technology and EducationTianjin · China2024 · 2 papers🏥West China Hospital of Sichuan UniversityChengdu · China2021–2023 · 2 papers🎓Xidian UniversityXi'an · China2023 · 2 papers🏢AmazonSeattle · United States2022 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 18 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. CoIR: A Comprehensive Benchmark for Code Information Retrieval Models (2025 · 29 citations)
   Most IR systems and benchmarks target natural-language search. Existing code retrieval benchmarks such as CodeSearchNet, CosQA and XcodeEval cover only a few task types and narrow domains, and they use inconsistent metrics. Many models also appear to be tuned to these leaderboards. The authors present CoIR, a…
2. RethinkMCTS: Refining Erroneous Thoughts in Monte Carlo Tree Search for Code Generation (2025 · 16 citations)
   The paper tackles a weakness of tree-search approaches to LLM code generation. Existing methods such as LATS search directly over code and handle mistakes through reflection, which piles up summaries of past errors in memory but never repairs the flawed reasoning itself. The authors propose RethinkMCTS, which runs…
3. GAPO: Robust Advantage Estimation for Real-World Code LLMs (2026 · 1 citation)
   Group-relative RL methods such as GRPO and DAPO are popular for post-training code LLMs because they need no critic.
4. PsyScore: A Psychometrically-Aware Framework for Trait-Adaptive Essay Scoring and ZPD-Scaffolded Feedback (2026 · 1 citation)
   Automated essay scoring systems usually separate grading from feedback. Neural scorers are hard to interpret, and LLM-generated comments ignore how skilled the writer is. PsyScore connects the two through one latent ability estimate θ drawn from Item Response Theory. A BERT encoder for each trait maps an essay to θ…

🤝 Co-authors here

12 of 17 co-authors with a page, the most papers together first.

• Ruiming Tang ×2
• Xinyi Dai ×2
• Yasheng Wang ×2
• Chanjin Zheng
• Hande Dong
• Hao Zhang
• Hong Wang
• Jianqing Zhang
• Kounianhua Du
• Kuicai Dong
• Qiang Lin
• Weinan Zhang

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

🔗 Cited by

Papers of our library cite their works 34 times (of the 149,439 papers whose bibliographies we read); 6 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/wei-xia/