About me

I am a third-year PhD candidate at Sydney Artificial Intelligence Centre, The University of Sydney, primarily advised by Prof. Tongliang Liu. I am also receiving valuable advice from Prof. Lei Feng. I regularly serve as a reviewer for ICLR, ICML, NeurIPS, TPAMI, and others.

My primary focus has been on “Generalization in Constrained Environments”. At present, most of my works are dedicated to promoting machine learning models that can effectively and efficiently generalize on large-scale, imperfect data, breaking through data bottlenecks. I welcome collaboration opportunities across all areas.

Selected Publications and Preprints

• Enhancing Sample Selection by Cutting Mislabeled Easy Examples.

  S. Yuan, L. Feng, B. Han, and T. Liu.

  arXiv preprint, 2025. [PDF]

• Instance-dependent Early Stopping.

  S. Yuan, R. Lin, L. Feng, B. Han, and T. Liu.

  International Conference on Learning Representations (ICLR), 2025. [PDF] [CODE]

  (Spotlight, Acceptance Rate: 5.1%)

• Early Stopping Against Label Noise Without Validation Data.

  S. Yuan, L. Feng, and T. Liu.

  International Conference on Learning Representations (ICLR), 2024. [PDF] [CODE]

• Late Stopping: Avoiding Confidently Learning from Mislabeled Examples.

  S. Yuan, L. Feng, and T. Liu.

  International Conference on Computer Vision (ICCV), 2023. [PDF] [CODE]

Educations

• 2022.09 - now, PhD student, School of Computer Science, The University of Sydney.
• 2018.09 - 2022.06, Undergraduate, School of Computer Science, Chongqing University.

Honors and Awards

• 12th China Youth Science and Technology Innovation Award, 100 recipients biennially, 2020
• Chongqing University Youth May·Fourth Medal, 5 recipients annually, 2020
• 26th China High Shcool Biology Olympiad, First Prize, ranked 12th, 2017