| Sep 18, 2025 |
One paper accepted at NeurIPS 2025: Adversarial Paraphrasing: A Universal Attack for Humanizing AI-Generated Text. See you in San Diego!
|
| Aug 20, 2025 |
Two papers accepted at EMNLP 2025 Main Conference:
|
| Jun 08, 2025 |
New paper on arXiv: Adversarial Paraphrasing: A Universal Attack for Humanizing AI-Generated Text. Many thanks to all my collaborators. Code released here.
|
| May 29, 2025 |
New paper on arXiv: DyePack: Provably Flagging Test Set Contamination in LLMs Using Backdoors
. Many thanks to all my collaborators. Code released here.
|
| May 23, 2025 |
New paper on arXiv: Gaming Tool Preferences in Agentic LLMs. Many thanks to all my collaborators. Code released here.
|
| Aug 26, 2024 |
I’ve started my PhD in Computer Science at the University of Maryland, where I am advised by Prof. Soheil Feizi.
|
| May 31, 2024 |
I’ve graduated from HKUST with the Academic Achievement Medal! Thank you to my parents, friends, and all my mentors!
|
| Sep 16, 2023 |
I have completed my first research paper, where we propose a simple yet effective clean-label backdoor attack for object detectors. Many thanks to Prof. Minhao Cheng for his invaluable support.
|