About me

I recently completed my PhD at the Sydney Artificial Intelligence Centre, School of Computer Science, The University of Sydney, advised by Prof. Tongliang Liu, in close collaboration with Prof. Lei Feng. I study overfitting in machine learning, and work on LLMs pre/post-training under imperfect supervision.

I am currently a student visitor at the Torr Vision Group at the University of Oxford, where I work on human-like LLMs. In late 2025, I visited the AI-for-X Centre at Nanyang Technological University, where I worked on overfitting in RLVR. Earlier in Singapore, I was a research officer at A*STAR CFAR, where I worked on overfitting in RLHF. I regularly serve as a reviewer for ICLR, ICML, NeurIPS, CVPR, ICCV, ECCV, UAI, AISTATS, as well as TPAMI, TIP, JAIR, TMLR, and MLJ. I am actively exploring postdoctoral research opportunities.

Selected Publications

• Mitigating Mismatch within Reference-based Preference Optimization.

  Suqin Yuan, Xingrui Yu, Jiyang Zheng, Lei Feng, Dadong Wang, Ivor Tsang, Tongliang Liu.

  International Conference on Learning Representations (ICLR), 2026. [PDF] [CODE]

• Instance-dependent Early Stopping for Adaptive Data Pruning.

  Suqin Yuan, Runqi Lin, Felix Azian, Lei Feng, Bo Han, Gang Niu, Masashi Sugiyama, Tongliang Liu.

  IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), accepted in 2026.

  Earlier version: Spotlight (top 5%) at International Conference on Learning Representations (ICLR), 2025. [PDF] [CODE]

• Enhancing Sample Selection Against Label Noise by Cutting Mislabeled Easy Examples.

  Suqin Yuan, Lei Feng, Bo Han, Tongliang Liu.

  Advances in Neural Information Processing Systems (NeurIPS), 2025. [PDF] [CODE]

• Early Stopping Against Label Noise Without Validation Data.

  Suqin Yuan, Lei Feng, Tongliang Liu.

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

• Late Stopping: Avoiding Confidently Learning from Mislabeled Examples.

  Suqin Yuan, Lei Feng, Tongliang Liu.

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

Educations

• 2022 - now, PhD student, School of Computer Science, The University of Sydney.
• 2018 - 2022, Undergraduate, School of Computer Science, Chongqing University.

Honors and Awards

• Gold Reviewer, International Conference on Machine Learning, 2026
• USYD Faculty of Engineering Career Advancement Award, 2025
• 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, 100 recipients biennially, 2020
• 26th China High School Biology Olympiad, First Prize, ranked 12th, 2017