Peilin Yu

CS @ Brown University. BATS Research Group.


CIT 351

115 Waterman St

Providence, RI 02905

I am a Ph.D. Candidate in Computer Science advised by Prof. Stephen Bach.

My main focus is on tackling weak supervision problems using approaches that involve working with limited, indirect, and/or noisy supervision while minimizing human effort. Additionally, I investigate the benefits of leveraging foundation models (GPTs, T5s, CLIP etc.) to enhance weak supervision workflow.

I am a proud 👐🏟🧀 Badger and I got my BS in CS and Math there in 2019.

Email : [first_name]_[last_name] [at] brown [dot] edu


Feb 27, 2023 We released Alfred, a toolkit for integrating Large Pretrained Models into Weak Supervision

selected publications

  1. ACL Demo
    Alfred: A System for Prompted Weak Supervision
    Yu, Peilin, and Bach, Stephen H.
    In ACL 2023
  2. ICLR
    Learning to Compose Soft Prompts for Compositional Zero-Shot Learning
    Yu, Peilin*, Nayak, Nihal V.*, and Bach, Stephen H. (* Co-first Author)
    International Conference on Learning Representations (ICLR) 2023
    Learning from Multiple Noisy Partial Labelers
    Yu, Peilin, Ding, Tiffany, and Bach, Stephen H.
    In Artificial Intelligence and Statistics (AISTATS) 2022
  4. ACL
    DIAG-NRE: A Neural Pattern Diagnosis Framework for Distantly Supervised Neural Relation Extraction
    Zheng, Shun, Han, Xu, Lin, Yankai, Yu, Peilin, Chen, Lu, Huang, Ling, Liu, Zhiyuan, and Xu, Wei
    In ACL 2019