Hello, I’m Yiming Wang (王一鸣).

I was born in Jiangsu Province, China, in August 2001. I’m now a second-year Ph.D. candidate at the Department of Computer Science and Engineering, Shanghai Jiao Tong University, supervised by Prof. Rui Wang. Before that, I received a Bachelor’s degree from the Institute of Artificial Intelligence, Beihang University.

📖 Educations

• 2023.09 - Present, Department of Computer Science and Engineering, Shanghai Jiao Tong University (SJTU), Shanghai, China
• 2019.09 - 2023.06, Institute of Artificial Intelligence, Beihang University (BUAA), Beijing, China

💻 Internships

• 2024.07 - Present, Tongyi Laboratory, Alibaba, Hangzhou.
  • Research Intern: Multi-lingual/modal LLMs; Mentor: Dr. Baosong Yang
• 2023.03 - 2023.09, Institute of AI Industry Research (AIR), Tsinghua University, Beijing.
  • Research Intern: AI for Science; Mentor: Prof. Hao Zhou
• 2021.11 - 2022.09, ACT Lab, Department of Computer Science and Engineering, Beihang University, Beijing.
  • Research Intern: Graph Learning / NLP; Mentor: Qianren Mao, Prof. Jianxin Li

🔬 Research

My research field is Natural Language Processing (NLP). Now I mainly focus on these areas oriented toward Large Language Models (LLMs) and Machine Learning (ML):

• Interpretable AI:
  • Behavioral Laws in the Latent Space (Chain-of-Embedding, ICLR 2025)
  • Controlled Meta-Behavioral Analysis like Physics
• Machine Reasoning:
  • Enhancing LLM Reasoning Ability and Efficiency (ST-BoN)
  • Evaluating the Boundaries of LLM Reasoning (PolyMath)

🔥 News

• 2025.04: 🎉We construct PolyMath, a challenging multilingual mathematical reasoning benchmark, used for standard evaluation by Qwen3.
• 2025.01: Two papers about Interpretable AI and Mathematical Reasoning are accepted by ICLR 2025.
• 2024.09: One paper about Mathematical Reasoning and Out-of-Distribution Detection is accepted by NeurIPS 2024.
• 2024.09: Two paper about Summarization and LLM Agent are accepted by EMNLP 2024.
• 2024.05: One paper about LLM Reasoning is accepted by ACL 2024.
• 2023.06: I earned my B.S. in Artificial Intelligence with a 1/31 overall ranking.
• 2023.05: One paper about LLM Summarization (SumCoT) is accepted by ACL 2023.
• 2022.08: One paper about Low-resource Summarization is accepted by COLING 2022.

📝 Selected Preprint

Reasoning, Evaluation

PolyMath: Evaluating Mathematical Reasoning in Multilingual Contexts

Yiming Wang, Pei Zhang, Jialong Tang, Haoran Wei, Baosong Yang, Rui Wang, Chenshu Sun, Feitong Sun, Jiran Zhang, Junxuan Wu, Qiqian Cang, Yichang Zhang, Fei Huang, Junyang Lin, Fei Huang, Jingren Zhou

Code Dataset Leaderboard

Reasoning

Sampling-Efficient Test-Time Scaling: Self-Estimating the Best-of-N Sampling in Early Decoding

Yiming Wang, Pei Zhang, Siyuan Huang, Baosong Yang, Zhuosheng Zhang, Fei Huang, Rui Wang

📝 Selected Publications

Interpretable AI, Trustworthy AI

Latent Space Chain-of-Embedding Enables Output-free LLM Self-Evaluation

Yiming Wang, Pei Zhang, Baosong Yang, Derek F. Wong, Rui Wang

[ICLR 2025] International Conference on Learning Representations

Code

Reasoning, Trustworthy AI

Embedding Trajectory for Out-of-Distribution Detection in Mathematical Reasoning

Yiming Wang, Pei Zhang, Baosong Yang, Derek F. Wong, Zhuosheng Zhang, Rui Wang

[NeurIPS 2024] Annual Conference on Neural Information Processing Systems

Code

Reasoning

Igniting Language Intelligence: The Hitchhiker’s Guide From Chain-of-Thought Reasoning to Language Agents

Zhuosheng Zhang, Yao Yao, Aston Zhang, Xiangru Tang, Xinbei Ma, Zhiwei He, Yiming Wang, Mark Gerstein, Rui Wang, Gongshen Liu, Hai Zhao

[ACM Computing Surveys] (SCI Q1, IF=23.8)

Code

Reasoning

Meta-Reasoning: Semantics-Symbol Deconstruction for Large Language Models

Yiming Wang, Zhuosheng Zhang, Pei Zhang, Baosong Yang, Rui Wang

[ACL 2024 Findings] Annual Meeting of the Association for Computational Linguistics

Code

Summarization

Element-aware Summarization with Large Language Models: Expert-aligned Evaluation and Chain-of-Thought Method

Yiming Wang, Zhuosheng Zhang, Rui Wang

[ACL 2023] Annual Meeting of the Association for Computational Linguistics

Code

Summarization

Noise-injected Consistency Training and Entropy-constrained Pseudo Labeling for Semi-supervised Extractive Summarization

Yiming Wang, Qianren Mao, Junnan Liu, Weifeng Jiang, Hongdong Zhu, Jianxin Li

[COLING 2022] International Conference on Computational Linguistics

Code

This is my first research paper, and also the last one on the eve of the LLM era.

💬 Service

• Reviewer: NeurIPS (2025-), ICLR (2025-), ACL Rolling Review (2024-), IEEE TASLP (2024-)
• Teaching Assistant:
  • Natural Language Processing and Large Language Model (for the John Class (SJTU), CS3966, 2024-)
  • Cognitive Basis (Beihang University, 2022)
  • Advanced Algebra (Beihang University, 2020-2022)

🎖 Honors and Awards

• 2023.06: Outstanding Graduate of Beijing (5%)
• 2023.01: Outstanding Teaching Assistant for Algebra Courses
• 2021.12: Ministry of Education-Huawei ``Future Star’’ Joint Commendation Scholarship
• 2020.12: The 1st prize in Beijing of the National College Student Mathematics Competition
• 2018.09: The 1st prize in Jiangsu Province of the Mathematical Competition of Senior High School of China