- Enhancing Sample Selection Against Label Noise by Cutting Mislabeled Easy Examples (NeurIPS 2025)
- Instance-dependent Early Stopping (ICLR 2025, selected for spotlight presentation, acceptance rate: 5%)
- Early Stopping Against Label Noise Without Validation Data (ICLR 2024)
- Late Stopping: Avoiding Confidently Learning from Mislabeled Examples (ICCV 2023)
- Honors and Awards:
- Top Reviewer Award, Annual Conference on Neural Information Processing Systems, 2025
- Top Reviewer Award, International Conference on Machine Learning, 2% in reviewers, 2025
- 12th China Youth Science and Technology Innovation Award, 2020
- Chongqing University Youth May·Fourth Medal, 2020
- 26th China High School Biology Olympiad, First Prize, ranked 12th, 2017
Research Experience
- Currently a Research Officer at A*STAR CFAR, Singapore, collaborating with Prof. Ivor Tsang and Dr. Xingrui Yu
Education
- 2022 - present, PhD student, School of Computer Science, The University of Sydney, Advisor: Prof. Tongliang Liu
- 2018 - 2022, Undergraduate, School of Computer Science, Chongqing University
Background
- Research Interests: Overfitting in Modern Deep Learning
- Professional Field: Generalization of machine learning models on large-scale, imperfect data
- Brief Introduction: A final-year PhD candidate at the Sydney Artificial Intelligence Centre, University of Sydney, focusing on enhancing the generalization ability of machine learning models.