🧑‍🔬 Fangzhen Lin

🏛️ Affiliations

🎓Hong Kong University of Science and TechnologyHong Kong · China1997–2026 · 111 papersEmploymentcurrent🎓University of TorontoToronto · Canada1993–1997 · 11 papers🎓Stanford UniversityStanford · United States1990–1995 · 5 papers🎓University of Hong KongPok Fu Lam · China1998–2019 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine.

🧭 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. VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning (2025 · 52 citations)
   Reasoning-focused "slow-thinking" systems such as OpenAI-o1 clearly beat fast models on text math, but on visual math benchmarks they do little better than strong vision-language models like Qwen2.5-VL-72B.
2. Beyond Distillation: Pushing the Limits of Medical LLM Reasoning with Minimalist Rule-Based RL (2025 · 10 citations)
   Medical LLMs usually learn to reason through supervised fine-tuning on chain-of-thought (CoT) traces, often distilled from proprietary systems such as GPT-4o.
3. To Code or not to Code? Adaptive Tool Integration for Math Language Models via Expectation-Maximization (2025 · 9 citations)
   Math-focused language models can reason in natural language (CoT) or offload computation to Python, but current hybrid systems such as Mammoth, Deepseek-Math and Qwen-2.5-Math decide poorly when to use code.

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. VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement LearningConference on Neural Information Processing Systems (NeurIPS)Haozhe Wang, Chao Qu, Zuming Huang, et al.2025 · 52 citations
2. AMR-DA: Data Augmentation by Abstract Meaning Representation ↗Findings of the Association for Computational Linguistics: ACL 2022 · no summary yetZiyi Shou, Yuxin Jiang, Fangzhen Lin2022 · 39 citations
3. Beyond Distillation: Pushing the Limits of Medical LLM Reasoning with Minimalist Rule-Based RLarXiv:2505.17952Che Liu, Haozhe Wang, Jiazhen Pan, et al.2025 · 10 citations
4. To Code or not to Code? Adaptive Tool Integration for Math Language Models via Expectation-MaximizationFindings of the Association for Computational LinguisticsHaozhe Wang, Long Li, Chao Qu, et al.2025 · 9 citations
5. Evaluate AMR Graph Similarity via Self-supervised Learning ↗Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yetZiyi Shou, Fangzhen Lin2023 · 7 citations
6. Incorporating EDS Graph for AMR Parsing ↗Proceedings of *SEM 2021: The Tenth Joint Conference on Lexical and Computational Semantics · no summary yetZiyi Shou, Fangzhen Lin2021 · 3 citations

🤝 Co-authors here

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

• Haozhe Wang ×3
• Chao Qu ×2
• Wei Chu ×2
• Che Liu
• Daniel Rueckert
• Jiazhen Pan
• Long Li
• Weidi Xu
• Wenhu Chen
• Yong Dai
• Zhongwei Wan
• Zuming Huang

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: Findings of the Association for Computational Linguistics 2025
• Conference on Neural Information Processing Systems (NeurIPS): NeurIPS 2025
• Findings of the Association for Computational Linguistics: ACL 2022
• Proceedings of *SEM 2021: The Tenth Joint Conference on Lexical and Computational Semantics
• Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

🔗 Cited by

Papers of our library cite their works 81 times (of the 149,439 papers whose bibliographies we read); 28 citing papers with a page here →.

Updated 3 November 2026

↑ back to top

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