🧑‍🔬 Mengdi Zhang

🏛️ Affiliations

🏢MeituanBeijing · China2019–2025 · 13 paperscurrent🎓Shandong University of Traditional Chinese MedicineJinan · China2025 · 3 paperscurrent🎓Jilin UniversityChangchun · China2024–2025 · 2 paperscurrent🏥Second Affiliated Hospital of Jilin UniversityChangchun · China2024–2025 · 2 paperscurrent🎓Peking UniversityBeijing · China2025 · 1 papercurrent🎓Singapore Management UniversitySingapore · Singapore2020–2023 · 4 papersEducation since 2020 · PhD, SCIS🎓Beijing University of Chemical TechnologyBeijing · China2016 · 2 papers🔬State Key Laboratory of Chemical Resource EngineeringBeijing · China2016 · 2 papers🎓Tsinghua UniversityBeijing · China2015 · 2 papers🎓University of Electronic Science and Technology of ChinaChengdu · China2015–2019Education 2015–2019 · Bachelor, Software Engineering

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. InftyThink: Breaking the Length Limits of Long-Context Reasoning in Large Language Models (2025 · 29 citations)
   Reasoning-oriented LLMs such as DeepSeek-R1 handle hard problems by writing very long chains of thought. This approach has three costs. Attention cost grows quadratically with output length. Generation can be cut off at the maximum context size before an answer appears. Quality also drops once text exceeds the short…
2. LogicPro: Improving Complex Logical Reasoning via Program-Guided Learning (2025 · 8 citations)
   Large language models often fail at multi-step logical reasoning when a task is posed in plain text, even when the same task is easy to solve with code.
3. SWE-Mutation: Can LLMs Generate Reliable Test Suites in Software Engineering? (2026 · 1 citation)
   Training and evaluating LLMs for software engineering depends on test suites, both for synthesizing repair trajectories and for providing reward signals in reinforcement learning.

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. Knowledge-aware Graph Neural Networks with Label Smoothness Regularization for Recommender Systems ↗ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD) · no summary yetHongwei Wang et al.2019 · 663 citations
2. Incorporating Dynamic Semantics into Pre-Trained Language Model for Aspect-based Sentiment Analysis ↗Findings of the Association for Computational Linguistics: ACL 2022 · no summary yetKai Zhang et al.2022 · 82 citations
3. InftyThink: Breaking the Length Limits of Long-Context Reasoning in Large Language ModelsarXiv:2503.06692Yuchen Yan, Yongliang Shen, Yang Liu, et al.2025 · 29 citations
4. LogicPro: Improving Complex Logical Reasoning via Program-Guided LearningAnnual Meeting of the Association for Computational Linguistics (ACL)Jin Jiang, Yuchen Yan, Yang Liu, et al.2025 · 8 citations
5. SWE-Mutation: Can LLMs Generate Reliable Test Suites in Software Engineering?Findings of the Association for Computational LinguisticsYuxuan Sun, Yuze Zhao, Yufeng Wang, et al.2026 · 1 citation

🤝 Co-authors here

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

• Jin Jiang ×2
• Yang Liu ×2
• Yuchen Yan ×2
• Jianing Wang
• Kai Zhang
• Xunliang Cai
• Yixin Cao
• Yongliang Shen
• Yueting Zhuang
• Yuxuan Sun
• Zhenya Huang
• Zhiyuan Ma

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): ACL 2025
• Findings of the Association for Computational Linguistics: Findings of the Association for Computational Linguistics 2026
• ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD)
• Findings of the Association for Computational Linguistics: ACL 2022

🔗 Cited by

Papers of our library cite their works 68 times (of the 149,439 papers whose bibliographies we read); 11 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/mengdi-zhang/