Mingyu Jin

About Me

I am a second-year Graduate student at the Department of Computer Science, Rutgers University-New Brunswick. My research interests lie in Explainable AI (XAI), with a focus on large language models (LLMs). Before that, I obtained my bachelor’s degree from the University of Liverpool.

Research Interests

Explainable AI, Natural Language Processing, Interpretability, Reason and Memory

News

• [1/2026] Paper Exploring Concept Depth: How Large Language Models Acquire Knowledge and Concept at Different Layers? was mentioned by the Deepseek V4 technique Report.
• [1/2026] One paper was accepted by EACL 2026 Industry Track.
• [9/2025] One paper was accepted by ENMLP 2025
• [8/2025] One paper was accepted by CIKM 2025 as short paper.
• [7/2025] One paper was accepted by COLM 2025
• [6/2025] I will join NEC Laboratories America as a research intern this summer.
• [5/2025] Two paper was accepted by ACL 2025
• [5/2025] One paper was accepted by ICML 2025
• [3/2025] two paper was accepted by SIGKDD Explorations Newsletter
• [1/2025] One papers accepted by NAACL 2025
• [1/2025] Two papers accepted by ICLR 2025
• [12/2024] One paper was accepted by SIGKDD Explorations Newsletter
• [11/2024] Check our new preprint about Disentangling Memory and Reasoning in LLM
• [11/2024] One paper was accepted by COLING 2025
• [10/2024] One paper was accepted by EMNLP 2024 Demo Track
• [09/2024] One paper was accepted by EMNLP 2024
• [09/2024] One paper was accepted by ICDM 2024
• [09/2024] One paper was accepted by ACML 2024
• [07/2024] One Paper was accepted by COLM 2024
• [07/2024] One paper was accepted by ECAI 2024 as Oral.
• [05/2024] One paper was accepted by ACL 2024
• [01/2024] Check Our Preprint: The Impact of Reasoning Step Length on Large Language Models about how Cot works.
• [12/2023] One paper was accepted by AAAI 2024

Internship

• NEC Labs America: Research Intern Advised by Wei Cheng, Princeton, NJ, June 2025 - Aug 2025

Services

• Conference reviewing: RecSys 2024, NeurIPS 2024, ICLR 2025, NAACL 2025, ACL 2025, NeurIPS 2025, COLM 2025, EMNLP 2025, EACL 2026, AAAI 2026, ICLR 2026, ACL ARR
• Journal reviewing: ACM TORS

Selected Publication

2026

• SAGE: An Agentic Explainer Framework for Interpreting SAE Features in Language Models (EACL 2026 Industry Track)

  Jiaojiao Han, Wujiang Xu, Mingyu Jin, Mengnan Du

    

2025

• Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understanding (ICML 2025)

  Mingyu Jin, Kai Mei, Wujiang Xu, Mingjie Sun, Ruixiang Tang, Mengnan Du, Zirui liu, Yongfeng Zhang

    

• Disentangling Memory and Reasoning Ability in Large Language Models (ACL 2025)

  Mingyu Jin, Weidi Luo, Sitao Cheng, Xinyi Wang, Wenyue Hua, Ruixiang Tang, William Yang Wang, Yongfeng Zhang

  

• Disentangling Logic: The Role of Context in Large Language Model Reasoning Capabilities (ACL Findings 2025)

  Wenyue Hua, Kaijie Zhu, Lingyao Li, Lizhou Fan, Shuhang Lin, Mingyu Jin, Haochen Xue, Zelong Li, JinDong Wang, Yongfeng Zhang

  

• SAE-SSV: Supervised Steering in Sparse Representation Spaces for Reliable Control of Language Models (EMNLP 2025)

  Zirui He, Mingyu Jin, Bo Shen, Ali Payani, Yongfeng Zhang, Mengnan Du

    

• Uncertainty is Fragile: Manipulating Uncertainty in Large Language Models (CIKM short 2025)

  Qingcheng Zeng, Mingyu Jin, Qinkai Yu, Zhenting Wang, Wenyue Hua, Guangyan Sun, Yanda Meng, Shiqing Ma, Qifan Wang, Felix Juefei-Xu, Kaize Ding, Fan Yang, Ruixiang Tang, Yongfeng Zhang

  

• Visual agents as fast and slow thinkers (ICLR 2025)

  Guangyan Sun🌟, Mingyu Jin🌟, Zhenting Wang, Chenglong Wang, Siqi Ma, Qifan Wang, YingNian Wu, Yongfeng Zhang, Dongfang Liu

  

• From Commands to Prompts: LLM-based Semantic File System for AIOS (ICLR 2025)

  Zeru Shi, Kai Mei, Mingyu Jin, Yongye Su, Chaoji Zuo, Wenyue Hua, Wujiang Xu, Yujie Ren, Zirui Liu, Mengnan Du, Dong Deng, Yongfeng Zhang

  

• Exploring Concept Depth: How Large Language Models Acquire Knowledge at Different Layers? (COLING 2025)

  Mingyu Jin, Qinkai Yu, Jingyuan Huang, Qingcheng Zeng, Zhenting Wang, Wenyue Hua, Haiyan Zhao, Kai Mei, Yanda Meng, Kaize Ding, Fan Yang, Mengnan Du, Yongfeng Zhang

    

• EmojiCrypt: Prompt Encryption for Secure Communication with Large Language Models (NAACL 2025)

  Guo Lin, Wenyue Hua, Zhenting Wang, Mingyu Jin, Yongfeng Zhang

  

• AIOS: LLM Agent Operating System (COLM 2025)

  Kai Mei, Xi Zhu, Wujiang Xu, Wenyue Hua, Mingyu Jin, Zelong Li, Shuyuan Xu, Ruosong Ye, Yingqiang Ge, Yongfeng Zhang

    

2024

• The Impact of Reasoning Step Length on Large Language Models (ACL Findings 2024)

  Mingyu Jin, Qinkai Yu, Dong Shu, Haiyan Zhao, Wenyue Hua, Yanda Meng, Yongfeng Zhang, Mengnan Du

  

• TrustAgent: Towards Safe and Trustworthy LLM-based Agents through Agent Constitution (EMNLP Findings 2024)

  Wenyue Hua, Xianjun Yang, Mingyu Jin, Wei Cheng, Ruixiang Tang, Yongfeng Zhang

    

• ProLLM: Protein Chain-of-Thoughts Enhanced LLM for Protein-Protein Interaction Prediction (COLM 2024)

  Mingyu Jin, Haochen Xue, Zhenting Wang, Boming Kang, Ruosong Ye, Kaixiong Zhou, Mengnan Du, Yongfeng Zhang

    

• Knowledge Graph Large Language Model (KG-LLM) for Link Prediction (ACML 2024)

  Dong Shu, Tianle Chen, Mingyu Jin, Mengnan Du, Yongfeng Zhang

    

• MathAttack: Attacking Large Language Models towards Math Solving Ability (AAAI 2024)

  Zihao Zhou, Qiufeng Wang, Mingyu Jin, Jie Yao, Jianan Ye, Wei Liu, Wei Wang, Xiaowei Huang, Kaizhu Huang

• Time Series Forecasting with LLMs: Understanding and Enhancing Model Capabilities (ACM SIGKDD Explorations)

  Hua Tang, Chong Zhang, Mingyu Jin, Qinkai Yu, Zhenting Wang, Yongfeng Zhang, Mengnan Du

Interest in Life

• DOTA2
• Basketball
• Travel

Powered by Jekyll and Minimal Light theme.