🧑‍🔬 Yihong Dong

🏛️ Affiliations

🎓Ningbo UniversityNingbo · China2004–2026 · 69 paperscurrent🎓Peking UniversityBeijing · China2022–2026 · 23 paperscurrent🏢Alibaba GroupHangzhou · China2025–2026 · 2 paperscurrent🎓Zhejiang UniversityHangzhou · China2004–2008 · 9 papers🎓Tongji UniversityShanghai · China2020–2021 · 6 papers🎓University of Electronic Science and Technology of ChinaChengdu · China2024–2025 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 5 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. CodeDPO: Aligning Code Models with Self Generated and Verified Source Code (2025 · 20 citations)
   Supervised fine-tuning helps code LLMs, but it does not reliably teach them to favor correct programs over flawed ones. It also does nothing to reward faster code. CodeDPO addresses both gaps with preference learning.
2. RL-PLUS: Countering Capability Boundary Collapse of LLMs in Reinforcement Learning with Hybrid-policy Optimization (2026 · 6 citations)
   RL-PLUS targets a known weakness of Reinforcement Learning with Verifiable Reward (RLVR). Standard on-policy training such as GRPO raises pass@1 but often lowers pass@k at large k. In other words, the tuned model solves fewer distinct problems than its base model, which the authors call capability boundary collapse.…
3. CODERL+: Improving Code Generation via Reinforcement with Execution Semantics Alignment (2026 · 5 citations)
   LLMs learn code by predicting text, but whether a program is correct depends on how it behaves when run. RLVR methods try to close this gap by rewarding programs that pass tests. A single pass/fail bit, however, gives little guidance about subtle logic errors such as mistracked loop variables.

All works

5 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. Self-planning Code Generation with Large Language Models ↗arXiv:2303.06689 · no summary yetXue Jiang et al.2023 · 223 citations
2. Generalization or Memorization: Data Contamination and Trustworthy Evaluation for Large Language Models ↗arXiv:2402.15938 · no summary yetYihong Dong et al.2024 · 123 citations
3. CodeDPO: Aligning Code Models with Self Generated and Verified Source CodeAnnual Meeting of the Association for Computational Linguistics (ACL)Kechi Zhang, Ge Li, Yihong Dong, et al.2025 · 20 citations
4. RL-PLUS: Countering Capability Boundary Collapse of LLMs in Reinforcement Learning with Hybrid-policy OptimizationAnnual Meeting of the Association for Computational Linguistics (ACL)Yihong Dong, Xue Jiang, Yongding Tao, et al.2026 · 6 citations
5. CODERL+: Improving Code Generation via Reinforcement with Execution Semantics AlignmentAnnual Meeting of the Association for Computational Linguistics (ACL)Xue Jiang, Yihong Dong, Mengyang Liu, et al.2026 · 5 citations

🤝 Co-authors here

12 of 14 co-authors with a page, the most papers together first.

• Zhi Jin ×3
• Ge Li ×2
• Kechi Zhang ×2
• Xue Jiang ×2
• Yongding Tao ×2
• Binhua Li
• Fei Huang
• Jing Su
• Jingjing Xu
• Jun Zhang
• Lili Mou
• Rongyu Cao

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 ×2, ACL 2025

🔗 Cited by

Papers of our library cite their works 163 times (of the 149,439 papers whose bibliographies we read); 28 citing papers with a page here →.

Updated 30 October 2026

↑ back to top

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