Publications

publications by categories in reversed chronological order.

2025

  1. Preprint 2025
    A Survey of Data Attribution: Methods, Applications, and Evaluation in the Era of Generative AI
    Junwei Deng*, Yuzheng† Hu*, Pingbang Hu*, Ting-Wei Li*, Shixuan Liu*, Jiachen T. Wang, Dan Ley, Qirun Dai, Benhao Huang, Jin Huang, Cathy Jiao, Hoang Anh Just, Yijun Pan, Jingyan Shen, Yiwen Tu, Weiyi Wang, Xinhe Wang, Shichang Zhang, Shiyuan Zhang, Ruoxi Jia, Himabindu Lakkaraju, Hao Peng, Weijing Tang, Chenyan Xiong, Jieyu Zhao, Hanghang Tong, Han Zhao, and Jiaqi W. Ma
    2025
  2. Preprint 2025
    Exploring Training Data Attribution under Limited Access Constraints
    Shiyuan Zhang*, Junwei Deng*, Juhan Bae, and Jiaqi W. Ma
    2025
  3. NeruIPS 2025
    Taming Hyperparameter Sensitivity in Data Attribution: Practical Selection Without Costly Retraining
    Weiyi Wang, Junwei Deng, Yuzheng Hu, Shiyuan Zhang, Xirui Jiang, Runting Zhang, Han Zhao, and Jiaqi W. Ma
    Advances in Neural Information Processing Systems, 2025
  4. Preprint 2025
    TimeCausality: Evaluating the Causal Ability in Time Dimension for Vision Language Models
    Zeqing Wang*, Shiyuan Zhang*, Chengpei Tang, and Keze Wang
    2025

2024

  1. NeurIPS 2024
    dattri: A Library for Efficient Data Attribution
    Junwei Deng*, Ting-Wei Li*, Shiyuan Zhang, Shixuan Liu, Yijun Pan, Hao Huang, Xinhe Wang, Pingbang Hu, Xingjian Zhang, and Jiaqi Ma
    Advances in Neural Information Processing Systems, 2024
    Spotlight Paper
  2. PACLIC 2024
    Nuanced Multi-class Detection of Machine-Generated Scientific Text
    Shiyuan Zhang, Yubin Ge, and Xiaofeng Liu
    38th Pacific Asia Conference on Language, Information and Computation, 2024

2023

  1. Preprint 2023
    Computational Copyright: Towards A Royalty Model for Music Generative AI
    Junwei Deng, Shiyuan Zhang, and Jiaqi Ma
    ICML 2024 GenLaw Workshop; DPFM Workshop at ICLR 2024, Best Paper Award, 2023