Publications

Selected and full publication list.

2026

  1. BA-LoRA: Bias-Alleviating Low-Rank Adaptation to Mitigate Catastrophic Inheritance in Large Language Models
    Yupeng Chang, Yi Chang, and Yuan Wu+
    In ICLR, 2026
    HTML Code
  2. AGGC: Adaptive Group Gradient Clipping for Stabilizing Large Language Model Training
    Zhiyuan Li, Yuan Wu+, and Yi Chang
    In Findings of ACL, 2026
    HTML Code
  3. BV-Blend: Uncertainty-Weighted Historical Baselines for Stable Critic-Free RL with Verifiable Rewards
    Yupeng Chang, Yuan Wu+, and Yi Chang
    In Findings of ACL, 2026
    HTML Code
  4. SOS-LoRA: Static Orthogonal-Subspace Low-Rank Adaptation with Fixed Multi-Scale Scaling
    Yupeng Chang, Yuan Wu+, and Yi Chang
    In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2026
    HTML Code
  5. A Survey of Retentive Network
    Haiqi Yang, Zhiyuan Li, Yi Chang, and Yuan Wu+
    In Findings of ACL, 2026
    HTML

2025

  1. Rethinking Data Selection at Scale: Random Selection is Almost All You Need
    Tingyu Xia, Bowen Yu, Kai Dang, An Yang, Yuan Wu+, Yuan Tian, Yi Chang, and Junyang Lin
    In Findings of EMNLP, 2025
    HTML Code
  2. StructFlowBench: A Structured Flow Benchmark for Multi-Turn Instruction Following
    Jinnan Li, Jinzhe Li, Yue Wang, Yi Chang, and Yuan Wu+
    In Findings of ACL, 2025
    HTML Code
  3. A Survey of RWKV
    Zhiyuan Li, Tingyu Xia, Yi Chang, and Yuan Wu+
    Neurocomputing, 2025
    HTML Code
  4. Selective Fine-Tuning for Large Language Models via Matrix Nuclear Norm
    Tingyu Xia, Yahan Li, Yuan Wu+, and Yi Chang
    Information Processing and Management, 2025
    HTML Code
  5. Large Language Model Evaluation via Matrix Nuclear-Norm
    Yahan Li, Tingyu Xia, Yi Chang, and Yuan Wu+
    In Findings of EMNLP, 2025
    HTML Code
  6. LoRA-MGPO: Mitigating Double Descent in Low-Rank Adaptation via Momentum-Guided Perturbation Optimization
    Yupeng Chang, Chenlu Guo, Yi Chang, and Yuan Wu+
    In Findings of EMNLP, 2025
    HTML Code
  7. NLoRA: Nystrom-Initiated Low-Rank Adaptation for Large Language Models
    Chenlu Guo, Yupeng Chang, and Yuan Wu+
    In Findings of EMNLP, 2025
    HTML Code
  8. R-LoRA: Random Initialization of Multi-Head LoRA for Multi-Task Learning
    Jinda Liu, Yupeng Chang, and Yuan Wu+
    In Findings of EMNLP, 2025
    HTML Code
  9. Don’t Take the Premise for Granted: Evaluating the Premise Critique Ability of Large Language Models
    Jinzhe Li, Gengxu Li, Yi Chang, and Yuan Wu+
    In Findings of EMNLP, 2025
    HTML Code
  10. Asymmetric Co-Training for Source-Free Few-Shot Domain Adaptation
    Gengxu Li and Yuan Wu+
    In PRCV, 2025
    HTML Code

2024

  1. A Survey on Evaluation of Large Language Models
    Yupeng Chang, Xu Wang, Jindong Wang, Yuan Wu+, Linyi Yang, Kaijie Zhu, Hao Chen, Xiaoyuan Yi, Cunxiang Wang, Yidong Wang, Wei Ye, Yue Zhang, Yi Chang, Philip S. Yu, Qiang Yang, and Xing Xie
    ACM Transactions on Intelligent Systems and Technology, 2024
    DOI HTML Code
  2. Language Models can Evaluate Themselves via Probability Discrepancy
    Tingyu Xia, Bowen Yu, Yuan Wu+, Yi Chang, and Chang Zhou
    In Findings of ACL, 2024
    HTML Code
  3. Regularized Conditional Alignment for Multi-Domain Text Classification
    Juntao Hu and Yuan Wu+
    In ICASSP, 2024
    HTML
  4. NegativePrompt: Leveraging Psychology for Large Language Models Enhancement via Negative Emotional Stimuli
    Xu Wang, Chao Li, Yupeng Chang, Jindong Wang, and Yuan Wu+
    In IJCAI, 2024
    HTML Code
  5. A Survey on Data Augmentation in Large Model Era
    Yue Zhou, Chenlu Guo, Xu Wang, Yi Chang, and Yuan Wu+
    arXiv preprint arXiv:2401.15422, 2024
    HTML Code
  6. Margin Discrepancy-Based Adversarial Training for Multi-Domain Text Classification
    Yuan Wu*+
    In CCF International Conference on Natural Language Processing and Chinese Computing, 2024
    HTML

2022

  1. Co-Regularized Adversarial Learning for Multi-Domain Text Classification
    Yuan Wu*, Diana Inkpen, and Ahmed El-Roby
    In AISTATS, 2022
    HTML
  2. Maximum Batch Frobenius Norm for Multi-Domain Text Classification
    Yuan Wu*, Diana Inkpen, and Ahmed El-Roby
    In ICASSP, 2022
    HTML

2021

  1. Mixup Regularized Adversarial Networks for Multi-Domain Text Classification
    Yuan Wu*, Diana Inkpen, and Ahmed El-Roby
    In ICASSP, 2021
    HTML
  2. Towards Category and Domain Alignment: Category-Invariant Feature Enhancement for Adversarial Domain Adaptation
    Yuan Wu*, Diana Inkpen, and Ahmed El-Roby
    In Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops, 2021
    HTML
  3. Conditional Adversarial Networks for Multi-Domain Text Classification
    Yuan Wu*, Diana Inkpen, and Ahmed El-Roby
    In Proceedings of the Second Workshop on Domain Adaptation for NLP, 2021
    HTML

2020

  1. Dual Adversarial Co-Learning for Multi-Domain Text Classification
    Yuan Wu* and Yuhong Guo
    In Proceedings of the AAAI Conference on Artificial Intelligence, 2020
    HTML
  2. Dual Mixup Regularized Learning for Adversarial Domain Adaptation
    Yuan Wu*, Diana Inkpen, and Ahmed El-Roby
    In Computer Vision – ECCV 2020, 2020
    HTML