Education

• Ph.D in Computer Science, University of California, Santa Cruz, 2019–Now
• M.S. in Data Science, Brown University, 2018–2019 (Graduate in advance)
• B.S. in Honors Science (Mathematics and Applied Mathematics), Xi’an Jiaotong University, 2014–2018
• High school in Honors Youth (Gifted Young), Xi’an Jiaotong University, 2012–2014

Work Experience

Research Intern, Bytedance AI Lab (June, 2023 – September, 2023)
Project topic: Trustworthy Large Language Model with Limited Human Efforts
Paper 1: Measuring and Reducing LLM Hallucination without Gold-Standard Answers via Expertise-Weighting
[Under Review]
Paper 2: Human-Instruction-Free LLM Self-Alignment with Limited Samples
[Under Review]

Student Researcher, Google Research Brain Team (June, 2022 – September, 2022)
Project topic: Class-imbalanced learing, Distributional robustness optimziation
Paper: Distributionally Robust Post-hoc Classifiers under Prior Shifts
[First authored paper published in ICLR 2023]

Student Researcher, Google Research Brain Team (March, 2022 – May, 2022)
Project topic: Learning with crowd-sourced noisy labels
Paper: To Aggregate or Not? Learning with Separate Noisy Labels
[First authored paper published in KDD 2023]

Selected Publications

Large Language Models

1. Measuring and Reducing LLM Hallucination without Gold-Standard Answers via Expertise-Weighting
   Jiaheng Wei, Yuanshun Yao, Jean-Francois Ton, Hongyi Guo, Andrew Estornell, Yang Liu
   (Under Review) [Category: LLM Evaluation; LLM Alignment; In-Context Learning; Supervised Fine-Tuning]

2. Human-Instruction-Free LLM Self-Alignment with Limited Samples
   Hongyi Guo, Yuanshun Yao, Wei Shen, Jiaheng Wei, Xiaoying Zhang, Zhaoran Wang, Yang Liu
   (Under Review) [paper] [Category: LLM Alignment; In-Context Learning]

Trustworthy Machine Learning

1. To Aggregate or Not? Learning with Separate Noisy Labels
   Jiaheng Wei*, Zhaowei Zhu*, Tianyi Luo, Ehsan Amid, Abhishek Kumar, Yang Liu
   KDD – ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2023
   [paper] [Category: Label Noise]

2. Distributionally Robust Post-hoc Clasifiers under Prior Shifts
   Jiaheng Wei, Harikrishna Narasimhan, Ehsan Amid, Wensheng Chu, Yang Liu, Abhishek Kumar
   ICLR – International Conference on Learning Representations, 2023
   [paper] [code] [Category: Long-Tailed Learning, Group-Dro]

3. To Smooth or Not? When Label Smoothing Meets Noisy Labels
   Jiaheng Wei, Hangyu Liu, Tongliang Liu, Gang Niu, Masashi Sugiyama, Yang Liu
   ICML (Long Presentation) – International Conference on Machine Learning, 2022
   [paper] [code] [Category: Label Noise]

4. Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotations
   Jiaheng Wei*, Zhaowei Zhu*, Hao Cheng, Tongliang Liu, Gang Niu, Yang Liu
   ICLR – International Conference on Learning Representations, 2022
   [paper] [data] [code] [Category: Label Noise]

5. When Optimizing f-divergence is Robust with Label Noise
   Jiaheng Wei and Yang Liu
   ICLR – International Conference on Learning Representations, 2021
   [paper] [code] [Category: Label Noise]

6. Fairness Improve Learning from Noisily Labeled Long-Tailed Data
   Jiaheng Wei, Zhaowei Zhu, Gang Niu, Tongliang Liu, Sijia Liu, Masashi Sugiyama, Yang Liu
   (Under Review) [paper] [Category: Long-Tailed Learning]

Incentives in Machine Learning

1. Sample Elicitation
   Jiaheng Wei*, Zuyue Fu*, Yang Liu, Xingyu Li, Zhuoran Yang, Zhaoran Wang
   AISTATS – International Conference on Artificial Intelligence and Statistics, 2021
   [paper] [code] [Category: Information Elicitation]

2. Auditing for Federated Learning: A Model Elicitation Approach
   Yang Liu, Rixing Lou, Jiaheng Wei [Alphabetical order] DAI – Distributed AI, 2023
   [paper] [Category: Information Elicitation]

Other Papers

1. DuelGAN: A Duel between Two Discriminators Stabilizes the GAN Training
   Jiaheng Wei*, Minghao Liu*, Jiahao Luo, Andrew Zhu, James Davis, Yang Liu
   ECCV – European Conference on Computer Vision, 2022
   [paper] [code] [Category: Deep Generative Models]

(*: denotes equal contributions)

Talks

• May, 2023 I gave an invited talk at AI-Time.

• Apr, 2023 I gave a invited talk at the TMLR Young Scientist Seminar.

• Mar, 2023 I gave a short talk in the Crowd Science workshop at WSDM 2023.

• Oct, 2022 I gave an invited talk from Domain Adaptation Team at University of Toronto.

• Aug, 2022 I gave an invited talk at AI-Time.

• Jul, 2022 I gave an oral presentation at ICML 2022 (Deep Learning: Robustness).

• Jun, 2022 I gave an invited talk at AI-Time.

• Nov, 2021 I gave a short talk in the Weakly Supervised Learning (WSL) workshop at ACML 2021.

Conference Reviews

• Reviewer:
  AAAI 2020, AISTATS 2021, CVPR 2021, ICCV 2021, NeurIPS 2021, ICLR 2022, CVPR 2022, ICML 2022, IJCAI 2023, KDD 2023, TMLR, TPAMI, NeurIPS 2023, etc.

• Organizer:
  A hands-on tutorial on learning with noisy labels at IJCAI 2023.
  1st Learning and Mining with Noisy Labels Challenge at IJCAI-ECAI 2022 [link].

Teaching Experience

• Teaching Assistant at UCSC CSE 242: Machine Learning. (Fall, 2021)
• Teaching Assistant at UCSC CSE 290-T: Computing for Society. (Spring, 2021)
• Teaching Assistant at UCSC CSE 142: Machine Learning. (Spring, 2020)

Honor and Awards

• The only recipient of Jack Baskin and Peggy Downes-Baskin Fellowship. (2023)
• Travel Grant from International Conference on Machine Learning (ICML). (2022)
• The First Prize of National Mount Everest Programme Scholarship in 2016-2017 Academic Year. (2017)
• The Second Prize of National Mount Everest Programme Scholarship in 2015-2016 Academic Year. (2016)
• The Second Prize in the 7th Chinese Mathematical Competitions. (2016)
• Xi’an Jiaotong Siyuan Scholarship in 2015-2016 Academic Year. (2015)
• Xi’an Jiaotong Siyuan Scholarship in 2014-2015 Academic Year. (2014)