I am a 4-th year Ph.D. student in Computer Science at the University of Washington, Seattle, advised by Prof. Ranjay Krishna and Prof. Alex Ratner. Before that, I was an undergraduate student in Computer Science at the University of Illinois Urbana-Champaign, where I was fortunate to be advised by Prof. Jiawei Han. In the past, I spent time at Microsoft Research and ByteDance AI Lab. I am a recipient of the 2024 Apple Scholars in AI/ML PhD fellowship (Data-centric AI track) and OpenAI Superalignment Fellowship.
Research Interests: My current research interests are interactive and data-centric AI/ML with an emphasis on faithful evaluation and effort-light approaches with applications in chemistry, biology, physics, etc. My past explorations lay at the intersection of machine learning, data mining, and natural language processing.
I am happy to mentor a few students on research and especially encourage students from underrepresented groups to reach out.
π AutoGen Blogs
π Selected Publications
(* denotes equal contribution)
Preprints
Peer-reviewed
- EcoAssistant: Using LLM Assistant More Affordably and Accurately
Jieyu Zhang, Ranjay Krishna, Ahmed Awadallah, Chi Wang.
LLM Agents @ ICLR 2024
- AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation Framework
Qingyun Wu, Gagan Bansal, Jieyu Zhang, Yiran Wu, Beibin Li, Erkang Zhu, Li Jiang, Xiaoyun Zhang, Shaokun Zhang, Jiale Liu, Ahmed Awadallah, Ryen White, Doug Burger, Chi Wang
LLM Agents @ ICLR 2024
Oral Presentation
- On the Trade-off of Intra-/Inter-class Diversity for Supervised Pre-training
Jieyu Zhang*, Bohan Wang*, Zhengyu Hu, Pang Wei Koh, Alexander Ratner.
NeurIPS 2023
- SugarCrepe: Fixing Hackable Benchmarks for Vision-Language Compositionality
Cheng-Yu Hsieh*, Jieyu Zhang*, Zixian Ma, Aniruddha Kembhavi, Ranjay Krishna
NeurIPS 2023
- Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Bias
Yue Yu*, Yuchen Zhuang*, Jieyu Zhang*, Yu Meng, Alexander Ratner, Ranjay Krishna, Jiaming Shen, Chao Zhang.
NeurIPS 2023
- DataComp: In Search of the Next Generation of Multimodal Datasets
34 authors.
NeurIPS 2023
Oral Presentation
- Leveraging Instance Features for Label Aggregation in Programmatic Weak Supervision
Jieyu Zhang*, Linxin Song*, Alexander Ratner.
AISTATS 2023
- Understanding Programmatic Weak Supervision via Source-aware Influence Function
Jieyu Zhang*, Haonan Wang*, Cheng-Yu Hsieh, Alexander Ratner.
NeurIPS 2022
- Creating Training Sets via Weak Indirect Supervision
Jieyu Zhang, Bohan Wang, Xiangchen Song, Yujing Wang, Yaming Yang, Jing Bai, Alexander Ratner.
ICLR 2022
- WRENCH: A Comprehensive Benchmark for Weak Supervision
Jieyu Zhang, Yue Yu, Yinghao Li, Yujing Wang, Yaming Yang, Mao Yang, Alexander Ratner.
NeurIPS 2021
Oral Presentation
Before Ph.D.
π Education
- University of Washington - Ph.D. in Computer Science 2020 - 2026 (expected).
- University of Illinois Urbana-Champaign - B.S. in Statistics and Computer Science.
π¨βπ» Industrial Experience
- Microsoft Research (Redmond) - Research Intern
2023.06-2023.9
Supervised by Dr. Chi Wang and Dr. Ahmed H. Awadallah.
- Microsoft Research (Asia) - Star Bridge Research Assistant
2020.09-2021.12
Supervised by Dr. Yujing Wang.
- ByteDance AI Lab - Research Intern
2020.04-2020.09
Supervised by Prof. Lei Li.
π
Awards
- OpenAI Superalignment Fellowship
- Apple Scholar in AI/ML PhD Fellowship
- Jane Street Graduate Research Fellowship Honorable Mention
- CRA Outstanding Undergraduate Researcher Honorable Mention
- ICDMβ20 Best Paper Award
- ICDMβ19 Student Travel Award
- UIUC James Scholar Preble Research Award
- UIUC John R. Pasta Outstanding Undergraduate Award
π Professional Services
- Leading organizer of Synthetic Data for Computer Vision Workshop @ CVPR 2024. [website]
- Reviewer: NeurIPS, ICML, ICLR, AAAI, IJCAI, CVPR, ACL, EMNLP, ARR, AISTATS, KDD, LOG.
Email: jieyuz2@cs.washington.edu
Twitter: @JieyuZhang20