Zhengyu Chen

Zhengyu Chen

Large Language Models & Trustworthy AI

Flag Counter

  • Hello! I am Zhengyu Chen.
  • I am a Senior Researcher at the LongCat Team of Meituan in Beijing. I obtained my Ph.D. degree in Computer Science & Technology from Zhejiang University in March 2023. During my Ph.D. studies, I also participated in the Qwen Team (formerly the M6 team) at Alibaba DAMO Academy from 2021-2023.
  • My research interests focus on Large Language Models (LLMs), Reinforcement Learning (RL), Natural Language Processing (NLP), and Trustworthy AI Systems. I have published 60+ research papers at top-tier conferences and journals including ICLR, ACL, ICML, NeurIPS, KDD, CVPR, EMNLP, etc., with citations according to Google Scholar. More details can be found in Publications and Google Scholar.
  • We are always actively recruiting highly motivated Full-Time Researchers and Research Interns! If interested, please contact me with your detailed CV!

🔥News

💻 Work Experience

  • Senior Researcher
    • LongCat Team, Meituan, China (2023 - Now)
    • Leading Large Language Models (LLMs) development.
  • Visiting Researcher
    • Qwen Team, Alibaba DAMO Academy, China (2021 - 2023)
    • Contributing to large-scale models: M6, OFA, and Qwen.
  • Research Assistant
    • Zhejiang University, College of Computer Science and Technology, China (2019 - 2023)
    • Ph.D. research in reinforcement learning, machine learning, and deep learning.

📝 Publications

This page shows selected recent publications. For a complete list, please visit my Google Scholar profile.

  • Global and Local Tensor Factorization for Multi-Criteria Recommender System
    Shuliang Wang, Jingting Yang, Zhengyu Chen, Hanning Yuan, Jing Geng, Zhen Hai
    Cell Patterns, 1(2): 100023 (Cell)

  • Revisiting Scaling Laws for Language Models: The Role of Data Quality and Training Strategies
    Zhengyu Chen, S Wang, Teng Xiao, Y Wang, S Chen, X Cai, J He, J Wang
    The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

  • SimPER: A Minimalist Approach to Preference Alignment without Hyperparameters
    Teng Xiao, Yige Yuan, Zhengyu Chen, Mingxiao Li, Shangsong Liang, Zhaochun Ren, Vasant G Honavar
    The 2025 International Conference on Learning Representations (ICLR 2025)

  • On a connection between imitation learning and RLHF
    Teng Xiao, Yige Yuan, Mingxiao Li, Zhengyu Chen, Vasant G Honavar
    The 2025 International Conference on Learning Representations (ICLR 2025)

  • Leveraging invariant principle for heterophilic graph structure distribution shifts
    Jinluan Yang, Zhengyu Chen, Teng Xiao, Yong Lin, Wenqiao Zhang, Kun Kuang
    Proceedings of the ACM Web Conference 2025 (WWW 2025)

  • Attributive reasoning for hallucination diagnosis of large language models
    Yuyan Chen, Zehao Li, Shuangjie You, Zhengyu Chen, Jingwen Chang, Yi Zhang, Weinan Dai, Qingpei Guo, Yanghua Xiao
    Proceedings of the 39th AAAI Conference on Artificial Intelligence (AAAI 2025)

  • Learning to reweight for generalizable graph neural network
    Zhengyu Chen, Teng Xiao, Kun Kuang, Zheqi Lv, Min Zhang, Jinluan Yang, Chengqiang Lu, Hongxia Yang, Fei Wu
    Proceedings of the 38th AAAI Conference on Artificial Intelligence (AAAI 2024)

  • Simple and asymmetric graph contrastive learning without augmentations
    Teng Xiao, Huai Zhu, Zhengyu Chen, Suhang Wang
    Advances in Neural Information Processing Systems 36 (NeurIPS 2024)

  • Intelligent model update strategy for sequential recommendation
    Zheqi Lv, Wenqiao Zhang, Zhengyu Chen, Shengyu Zhang, Kun Kuang
    Proceedings of the ACM Web Conference 2024 (WWW 2024)

  • Mapo: Boosting large language model performance with model-adaptive prompt optimization
    Yuyan Chen, Zhihao Wen, Ge Fan, Zhengyu Chen, Wei Wu, Dayiheng Liu, Zhixu Li, Bang Liu, Yanghua Xiao
    EMNLP 2023 Findings of the Association for Computational Linguistics (EMNLP 2024)

  • Mitigating the Backdoor Effect for Multi-Task Model Merging via Safety-Aware Subspace
    Jinluan Yang, Anke Tang, Didi Zhu, Zhengyu Chen, Li Shen, Fei Wu
    2024 International Conference on Learning Representations (ICLR 2024)

  • Transferring causal mechanism over meta-representations for target-unknown cross-domain recommendation
    Shengyu Zhang, Qiaowei Miao, Ping Nie, Mengze Li, Zhengyu Chen, Fuli Feng, Kun Kuang, Fei Wu
    ACM Transactions on Information Systems 42 (4), 1-27 (TOIS 2024)

  • Let’s Ask GNN: Empowering Large Language Model for Graph In-Context Learning
    Zhengyu Hu, Yichuan Li, Zhengyu Chen, Jingang Wang, Han Liu, Kyumin Lee, Kaize Ding
    Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP 2024)

  • Scaling laws across model architectures: A comparative analysis of dense and MoE models in large language models
    Siqi Wang, Zhengyu Chen, Bei Li, Keqing He, Min Zhang, Jingang Wang
    Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP 2024)

  • Robustness Evaluation of Multi-Agent Reinforcement Learning Algorithms using Gaussian Noise Attacks
    Xusheng Zhang, Wei Zhang, Zhengyu Chen, Sihong He
    2023 International Conference on Learning Representations (ICLR 2023)

  • DUET: A Tuning-Free Device-Cloud Collaborative Parameters Generation Framework for Efficient Device Model Generalization
    Zheqi Lv, Wenqiao Zhang, Shengyu Zhang, Zhengyu Chen, Tao Shen, Hongxia Yang, Beng Chin Ooi, Fei Wu
    Proceedings of the ACM Web Conference 2023 (WWW 2023)

  • Reconsidering Learning Objectives in Unbiased Recommendation: A Distribution Shift Perspective
    Teng Xiao, Zhengyu Chen, and Suhang Wang
    Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2023)

  • BA-GNN: On Learning Bias-Aware Graph Neural Network
    Zhengyu Chen, Teng Xiao, Kun Kuang
    38th IEEE International Conference on Data Engineering (ICDE 2022)

  • Learn Goal-Conditioned Policy with Intrinsic Motivation for Deep Reinforcement Learning
    Jinxin Liu, Dong Wang, Qi Tian, Zhengyu Chen
    Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI 2022)

  • The Role of Deconfounding in Meta-learning
    Yinjie Jiang, Zhengyu Chen, Luotian Yuan, Ying Wei, Kun Kuang, Fei Wu
    Proceedings of the 39th International Conference on Machine Learning (ICML 2022)

  • Decoupled Self-supervised Learning for Non-Homophilous Graphs
    Teng Xiao, Zhengyu Chen, Zhimeng Guo, Zeyang Zhuang, Suhang Wang
    Conference on Neural Information Processing Systems (NeurIPS 2022)

  • Pareto Self-Supervised Training for Few-Shot Learning
    Zhengyu Chen, Jixie Ge, Heshen Zhan, Donglin Wang
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2021)

  • Deep transfer tensor decomposition with orthogonal constraint for recommender systems
    Zhengyu Chen, Ziqing Xu, and Donglin Wang
    Proceedings of the 35th AAAI Conference on Artificial Intelligence (AAAI 2021)

  • Learning How to Propagate Messages in Graph Neural Networks
    Teng Xiao, Zhengyu Chen, Donglin Wang and Suhang Wang
    ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2021)

Academic Services

  • Review Assignments:
    • International Conference on Learning Representations (2023 - Now)
    • International Conference on Machine Learning (ICML) (2023 - Now)
    • International Conference on Neural Information Processing Systems (NeurIPS) (2023 - Now)
    • ACM Transactions on Information Systems (TOIS) (2020 - Now)
    • IEEE Transactions on Cybernetics (TCYB) (2021 - Now)
    • IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2022 - Now)
    • IEEE International Conference on Computer Vision (ICCV) (2022 - Now)
    • ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (2021 - Now)
    • Association for the Advancement of Artificial Intelligence (AAAI) (2021 - Now)
    • International Joint Conference on Artificial Intelligence (IJCAI) (2021 - Now)
    • IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2021 - Now)
    • ACM International Conference on Multimedia (MM) (2022 - Now)
  • Professional Memberships:
    • Member of IEEE, ACM, AAAI, and ACL (2020 - Now)

Talks