Greetings, I am a graduate student in the Department of Computer Science Engineering (HKUST) under the co-supervision of Prof. Yi R. (May) Fung and Prof. Minhao Cheng. My interest lies broadly in (Trustworthy) Machine Learning in Large Models.

Education

• 2023 - present: Computer Science, HKUST
• 2018 - 2022: B.Eng. in Telecommunication, BUPT & QMUL

Internship

• 2021.10 - 2022.08: Research Intern, SenseTime Research
• 2024.05 - present: Research Intern, Sea AI Lab (hosted by Tianyu Pang and Chao Du)

Publications

* denotes equal contribution

• RM-Bench: Benchmarking Reward Models of Language Models with Subtlety and Style [pdf] [code]
  Yantao Liu, Zijun Yao, Rui Min, Yixin Cao, Lei Hou, Juanzi Li, In International Conference on Learning Representations (ICLR), 2025. (Oral)

• Uncovering, Explaining, and Mitigating the Superficial Safety of Backdoor Defense [pdf] [code]
  Rui Min*, Zeyu Qin*, Nevin L. Zhang, Li Shen, Minhao Cheng, In Advances in Neural Information Processing Systems (NeurIPS), 2024. (Spotlight)

• A Watermark-Conditioned Diffusion Model for IP Protection [pdf] [code]
  Rui Min, Sen Li, Hongyang Chen, Minhao Cheng, In European Conference on Computer Vision (ECCV), 2024.

• Towards Stable Backdoor Purification with Feature Shift Tuning [pdf] [code]
  Rui Min*, Zeyu Qin*, Li Shen, Minhao Cheng, In Advances in Neural Information Processing Systems (NeurIPS), 2023.

• Identification of the Adversary from a Single Adversarial Example [pdf] [code]
  Minhao Cheng, Rui Min, Haochen Sun, Pin-Yu Chen, In International Conference on Machine Learning (ICML), 2023. (A short version appears in NeurIPS Workshop on Machine Learning Safety, 2022)

Preprints

• Pairwise RM: Perform Best-of-N Sampling with Knockout Tournament [arXiv] [code]
  Yantao Liu, Zijun Yao, Rui Min, Yixin Cao, Lei Hou, Juanzi Li

• Improving Your Model Ranking on Chatbot Arena by Vote Rigging [arXiv] [code]
  Rui Min*, Tianyu Pang*, Chao Du, Qian Liu, Minhao Cheng, Min Lin, In ICLR Workshop on Foundation Models in the Wild, 2025.

• Universal Backdoor Attacks Detection via Adaptive Adversarial Probe [arXiv]
  Yuhang Wang, Huafeng Shi, Rui Min, Ruijia Wu, Siyuan Liang, Yichao Wu, Ding Liang, Aishan Liu

Services

• Reviewer: AAAI; ICML; NeurIPS; ICLR