🧑‍🔬 Houxing Ren

🏛️ Affiliations

🎓Chinese University of Hong KongHong Kong · China2023–2026 · 13 paperscurrent🔬Centre for Perceptual and Interactive IntelligenceHong Kong · China2026 · 1 papercurrent🎓Beihang UniversityBeijing · China2021–2023 · 9 papersEmployment🔬Peng Cheng LaboratoryShenzhen · China2021–2022 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 2 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. MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning (2023 · 99 citations)
   Open-source LLMs do much worse than proprietary systems such as GPT-4 Code Interpreter on school and competition math.
2. Step-Controlled DPO: Leveraging Stepwise Error for Enhanced Mathematical Reasoning (2024 · 23 citations)
   Standard DPO for math reasoning labels whole solutions as good or bad based only on the final answer. This coarse signal does not show the model where a reasoning chain breaks down, and human step-level annotation is costly. The authors propose Step-Controlled DPO (SCDPO), which builds step-level error supervision…
3. MathCanvas: Intrinsic Visual Chain-of-Thought for Multimodal Mathematical Reasoning (2026 · 3 citations)
   Text-only chain-of-thought is a poor fit for areas such as geometry and function analysis, where people solve problems by sketching and modifying diagrams.
4. Towards Robust Real-World Spreadsheet Understanding with Multi-Agent Multi-Format Reasoning (2026)
   Spreadsheets used in business, auditing and science are often very large. They also carry meaning through layout: multi-level headers, merged cells, several sheets, and colour or shading. Most LLM methods flatten tables into plain text, which loses these cues and can exceed the context window. The authors present…

All works

6 works of theirs in our library, the most cited first; 4 with a page here, the others link their original until we summarise them.

1. MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical ReasoningarXiv:2310.03731Ke Wang, Houxing Ren, Aojun Zhou, et al.2023 · 99 citations
2. MathGenie: Generating Synthetic Data with Question Back-translation for Enhancing Mathematical Reasoning of LLMs ↗Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yetZimu Lu et al.2024 · 58 citations
3. Step-Controlled DPO: Leveraging Stepwise Error for Enhanced Mathematical ReasoningarXiv:2407.00782Zimu Lu, Aojun Zhou, Ke Wang, et al.2024 · 23 citations
4. MathCoder2: Better Math Reasoning from Continued Pretraining on Model-translated Mathematical Code ↗arXiv:2410.08196 · no summary yetZimu Lu et al.2024 · 19 citations
5. MathCanvas: Intrinsic Visual Chain-of-Thought for Multimodal Mathematical ReasoningAnnual Meeting of the Association for Computational Linguistics (ACL)Weikang Shi, Aldrich Yu, Rongyao Fang, et al.2026 · 3 citations
6. Towards Robust Real-World Spreadsheet Understanding with Multi-Agent Multi-Format ReasoningAnnual Meeting of the Association for Computational Linguistics (ACL)Houxing Ren, Mingjie Zhan, Zimu Lu, et al.2026

🤝 Co-authors here

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

• Ke Wang ×4
• Zimu Lu ×4
• Aojun Zhou ×3
• Hongsheng Li ×3
• Mingjie Zhan ×3
• Weikang Shi ×3
• Junting Pan
• Linqi Song
• Renrui Zhang
• Rongyao Fang
• Sichun Luo
• Yuxuan Hu

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

🔗 Cited by

Papers of our library cite their works 183 times (of the 149,439 papers whose bibliographies we read); 35 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/houxing-ren/