Peilin Yu

Apple Inc.

I’m a research engineer at Apple, where I work on advancing multimodal intelligence technologies. My work focuses on building scalable systems that integrate language, vision, and other modalities in support of practical, user-facing AI experiences.

I received my Ph.D. in Computer Science from Brown University in 2025, advised by Prof. Stephen Bach. My research explores how to improve data strategy and annotation efficiency with weak supervision using foundation models, particularly in settings with noisy, limited or indirect supervision.

Previously, I interned at Microsoft Azure AI, where I worked on adapting multimodal large language models to improve performance across downstream tasks.

I’m also a proud 👐🏟🧀 Badger, having earned my B.S. in Computer Sciences and Mathematics from the University of Wisconsin–Madison in 2019. Outside of research, I’m a certified FAA Private Pilot and broadly interested in aviation.

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

news

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

selected publications

NeurIPS-ENLSP

Structure Discovery in Prompted Weak Supervision

Yu, Peilin*, Su, Jinyan*, Zhang, Jieyu, and Bach, Stephen H. (* Co-first Author)

In The 3rd NeurIPS Workshop on Efficient Natural Language and Speech Processing 2023

Bib

@inproceedings{yu2023sdpws,
  abbr = {NeurIPS-ENLSP},
  title = {Structure Discovery in Prompted Weak Supervision},
  author = {Yu, Peilin* and Su, Jinyan* and Zhang, Jieyu and Bach, Stephen H. (* Co-first Author)},
  booktitle = {The 3rd NeurIPS Workshop on Efficient Natural Language and Speech Processing},
  year = {2023},
  bibtex_show = {true},
  selected = {true}
}

IEEE Big Data

Leveraging Large Language Models for Structure Learning in Prompted Weak Supervision

Yu, Peilin*, Su, Jinyan*, Zhang, Jieyu, and Bach, Stephen H. (* Co-first Author)

In IEEE International Conference on Big Data 2023

Bib

@inproceedings{yu2023lllmpws,
  abbr = {IEEE Big Data},
  title = {Leveraging Large Language Models for Structure Learning in Prompted Weak Supervision},
  author = {Yu, Peilin* and Su, Jinyan* and Zhang, Jieyu and Bach, Stephen H. (* Co-first Author)},
  booktitle = {IEEE International Conference on Big Data},
  year = {2023},
  bibtex_show = {true},
  selected = {true}
}

ACL Demo

Alfred: A System for Prompted Weak Supervision

Yu, Peilin, and Bach, Stephen H.

In ACL 2023

Bib Code

@inproceedings{yu2023alfred,
  abbr = {ACL Demo},
  title = {Alfred: A System for Prompted Weak Supervision},
  author = {Yu, Peilin and Bach, Stephen H.},
  booktitle = {ACL},
  year = {2023},
  bibtex_show = {true},
  selected = {true},
  code = {https://github.com/batsresearch/alfred}
}

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

PDF Code

AISTATS

Learning from Multiple Noisy Partial Labelers

Yu, Peilin, Ding, Tiffany, and Bach, Stephen H.

In Artificial Intelligence and Statistics (AISTATS) 2022

Bib PDF Code

@inproceedings{yu2022nplm,
  abbr = {AISTATS},
  title = {Learning from Multiple Noisy Partial Labelers},
  author = {Yu, Peilin and Ding, Tiffany and Bach, Stephen H.},
  booktitle = {Artificial Intelligence and Statistics (AISTATS)},
  year = {2022},
  bibtex_show = {true},
  selected = {true},
  pdf = {2106.04530.pdf},
  code = {https://github.com/batsresearch/nplm}
}

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

Bib PDF Code

@inproceedings{zheng2019diagnre,
  abbr = {ACL},
  title = {DIAG-NRE: A Neural Pattern Diagnosis Framework for Distantly Supervised Neural Relation Extraction},
  author = {Zheng, Shun and Han, Xu and Lin, Yankai and Yu, Peilin and Chen, Lu and Huang, Ling and Liu, Zhiyuan and Xu, Wei},
  booktitle = {ACL},
  year = {2019},
  bibtex_show = {true},
  selected = {true},
  pdf = {1811.02166.pdf},
  code = {https://github.com/thunlp/DIAG-NRE}
}