Xiaomeng Hu

BIOGRAPHY

I am currently a second-year Ph.D. student at the Department of Computer Science and Engineering of The Chinese University of Hong Kong under the supervision of Prof. Tsung-Yi Ho and co-supervised by Dr. Pin-Yu Chen from IBM-Research. Previously, I had the fortune to collaborate with researchers from Microsoft Research Redmond, Tsinghua University and Northeastern University. I received my B.Eng. from Northeastern Univ in July 2023.

Sep. 2024 Accept ICLR 2025 reviewer invitations..
Sep. 2024 Gradient Cuff was accepted by NeurIPS 2024. Thank all the co-authors!.
Sep. 2023 RADAR was accepted by NeurIPS 2023. Thank all the co-authors!.
Aug. 2023 Embark on my new life journey at CUHK.
Jun. 2023 Graduated from NEU. Thanks all!
Apr. 2022 One paper was accepted by SIGIR 2022. Thank all the co-authors!

Ph.D. Computer Science and Engineering, The Chinese University of Hong Kong, Aug. 2023 -
B.Eng. Artificial Intelligence, Northeastern University, Sep. 2019 - Jul. 2023

* denotes equal contribution.

[P1] Xiaomeng Hu, Pin-Yu Chen, Tsung-Yi Ho. Token Highlighter: Inspecting and Mitigating Jailbreak Prompts for Large Language Models.

[C1] Xiaomeng Hu*, Shi Yu*, Chenyan Xiong, Zhenghao Liu, Zhiyuan Liu, Ge Yu. P³ Ranker: Mitigating the Gaps between Pre-training and Ranking Fine-tuning with Prompt-based Learning and Pre-finetuning. SIGIR 2022. (paper) (code)
[C2] Xiaomeng Hu, Pin-Yu Chen, Tsung-Yi Ho. RADAR: Robust AI-Text Detection via Adversarial Learning. NeurIPS 2023. (paper) (demo) (code)
[C3] Xiaomeng Hu, Pin-Yu Chen, Tsung-Yi Ho. Gradient Cuff: Detecting Jailbreak Attacks on Large Language Models by Exploring Refusal Loss Landscapes. NeurIPS 2024. (paper) (demo) (code)

The Chinese University of Hong Kong, Hong Kong SAR, Feb. 2023 - Jun. 2023
Research Assistant, IDEA Lab
Topic: AI-text detection
Tsinghua University, Beijing, P.R. China, Aug. 2021 - Jun. 2022
Research Assistant, THU-NLP Lab
Topic: Prompt learning for efficient Information Retrieval