About

Dr. Changyi Ma joined the School of Artificial Intelligence at Jilin University (JLU) in 2025 as a tenure-track Associate Professor. She received her Ph.D. degree from The Chinese University of Hong Kong (QS #36, 2025), advised by Prof. Shuguang Cui (IEEE Fellow) and Prof. Wenye Li, and received the Presidential Award for Outstanding Doctoral Student of CUHK-Shenzhen 2022. Her research interests include Information Retrieval, Similarity Matrix Calibration, Continual Learning, and Large Language Models (LLMs). I am always looking for self-motivated PhD/RA/Visiting/Master students.
Please send me an email to query the detail: changyima@jlu.edu.cn.

Research Interests

  • Information Retrieval
  • Similarity Matrix Calibration
  • Continual Learning and Large Language Models (LLMs)
  • Embodied Optimization and Generalization
  • Physical Artificial Itelligence

News

2026.08 One paper is accepted by CIKM (CCF B)! Many Congratulations to Yingying Wu.
2026.08 One paper is accepted by EMNLP Findings (CCF B)! Many Congratulations to Yicheng Zhao and Yingying Wu.
2026.06 One paper is accepted by ECCV (CCF B)! .
2026.06 One paper is accepted by IEEE TKDE (CCF A)!
2026.05 Two papers are accepted by ICML (CCF A)!
2025.09 One paper is accepted by NeurIPS (CCF A)!
2025.05 One paper is accepted by ACL Findings (CCF A)!
2024.01 One paper is accepted by TheWebConf (CCF A)!
2023.12 One paper is accepted by ACM TIST (JCR Q1)!

Selected Publications

  • A Low-Rank Perspective on Similarity Matrix Completion (TKDE 2026, CCF A) .
    Changyi Ma, Runsheng Yu, Xiao Chen, Youzhi Zhang, Zhen Lei.

  • Deep Noisy-Label Learning via Effective Rank Reduction (ECCV 2026, CCF B) .
    Changyi Ma, Zihan Fang, Lihua Zhou, Tao Li, Wenyu Liu, Runsheng Yu, Xuan Song.

  • Diagnosing Parametric Contamination in LoRA-Based RAG Distillation. (CIKM 2026, CCF B)
    Yingying Wu, Xiao Chen, Changyi Ma*, Xuan Song.

  • RecToolBench: Benchmarking Recommendation-Specific Tool Orchestration under Fuzzy User Intentions. (EMNLP 2026, CCF B)
    Xiao Chen, Yicheng Zhao, Yingying Wu, Zhendong Chu, Changyi Ma*, Qingsong Wen, Xuan Song.

  • Reinforcement Fine-Tuning Naturally Mitigates Forgetting in Continual Post-Training. (ICML 2026, CCF A)
    Song Lai, Haohan Zhao, Rong Feng, Changyi Ma, Wenzhuo Liu, Hongbo Zhao, Xi Lin, Dong Yi, Min Xie, Qingfu Zhang, Hongbin Liu, Gaofeng Meng, Fei Zhu.

  • Lookahead-GCG: Improving Universal Multi-Model Optimization-Based Jailbreaking Attacks via Stochastic Nesterov Optimization. (ICML 2026, CCF A)
    Rong Feng, Haohan Zhao, Shiqin Tang, Geng Liu, Song Lai, Meng Wang, Shuxin Zhuang, Yuqi Zha, Changyi Ma, Runsheng Yu

  • Gradient-Guided Epsilon Constraint Method for Online Continual Learning. (Neruips 2025, CCF A)
    Song Lai1, Changyi Ma1, Fei Zhu, Zhe Zhao, Xi Lin, Gaofeng Meng, Qingfu Zhang.

  • C2KD: Cross-layer and Cross-head Knowledge Distillation for Small Language Model-based Recommendation. (ACL 2025 Findings, CCF A)
    Xiao Chen1, Changyi Ma1, Wenqi Fan, Zhaoxiang Zhang, Qing Li.

  • A Fast Similarity Matrix Calibration Method with Incomplete Query. (TheWebConf 2024, CCF A, Oral)
    Changyi Ma1, Runsheng Yu1, Youzhi Zhang.

  • Learning Sparse Binary Code for Maximum Inner Product Search. (CIKM 2021, CCF B)
    Changyi Ma, Fangchen Yu, Yueyao Yu, Wenye Li.
    CIKM'21 Best Short Paper Finalist

  • Large-scale Image Retrieval with Sparse Binary Projections. (SIGIR 2020, CCF A)
    Changyi Ma, Chonglin Gu, Wenye Li, Shuguang Cui.

Current Students

PhD Students

  • 26 Fall: Mr.Zhiqiang Guo (MLLM)
  • 25 Fall: Mr.Yicheng Zhao (LLM Agents) , Mr.Bicong Sang (Evolutionary Computing)

Master Students

  • 26 Fall: Mr.Bingyu Cao (Continual Learning), Mr.Zishan Zhao (LLM Agents) , Mr.Fulin Min, Mr.Wenjun Chen
  • 25 Fall: Mr.Yingying Wu (LLM Agents), Mr.Kaiquan Hu (LLM Agents), Mr.Liangenrong Shi (AI4Sci), Mr.Hanran Zhou (LLM Agents)

Undergraduate Students

  • 25 Fall: Mr.Zijie Xi (AI4PDE), Mr.Yibo Wang (AI4PDE)
  • 24 Fall: Miss.Chang Wang(LLM Agents & Security), Mr.Ruoyu Zhang (LLM Agents & Security), Mr.Huiyu Gong (Continual Learning)