Research Focus

My research focuses on neural information retrieval with large language models and transformer-based dense and sparse models. In addition to model training, I also work on efficient retrieval architectures and algorithms.

Education

Publications

  • Low-Cost Document Retrieval with Dense Pseudo-Query Encoding

    Shanxiu He, Wentai Xie, Yifan Qiao, Parker Carlson, Tao Yang

    SIGIR 2025 — Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval

  • Dynamic Superblock Pruning for Fast Learned Sparse Retrieval

    Parker Carlson, Wentai Xie, Shanxiu He, Tao Yang

    SIGIR 2025 — Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval

  • LSTM-based Selective Dense Text Retrieval Guided by Sparse Lexical Retrieval

    Yingrui Yang, Parker Carlson, Yifan Qiao, Wentai Xie, Shanxiu He, Tao Yang

    ECIR 2025 — Proceedings of the 47th European Conference on Information Retrieval

  • Balanced Knowledge Distillation with Contrastive Learning for Document Re-ranking

    Yingrui Yang, Shanxiu He, Yifan Qiao, Wentai Xie, Tao Yang

    ICTIR 2023 — ACM SIGIR International Conference on the Theory of Information Retrieval

  • Efficient Sparse Retrieval with Lightweight Superblock Pruning

    Parker Carlson, Wentai Xie, Tao Yang under review

    ManuscriptOctober 2025

Contact

  • Address

    University of Santa Barbara
    Santa Barbara, CA
    United States
  • Email

    wentaixie@ucsb.edu