Home | Twitter / X | Google Scholar ｜Xiaohongshu
About me and featured research
Blogs
Random blog checkpoint here. ⬇️:
Shu’s blog
News
- 🎄 2025.8 Our paper “RepreGuard: Detecting LLM-Generated Text by Revealing Hidden Representation Patterns” was accepted by TACL
- 🌱 2025.6 Our new preprint “A Survey on the Safety and Security Threats of Computer-Using Agents: JARVIS or Ultron?” released ****https://arxiv.org/abs/2505.10924
- 🎄2025.5 Three papers was accepted by ACL2025
- Fraud-R1 : A Multi-Round Benchmark for Assessing the Robustness of LLM Against Augmented Fraud and Phishing Inducements paper |github
- Understanding the Repeat Curse in Large Language Models from a Feature Perspective paper | github
- Rethinking Prompt-based Debiasing in Large Language Models
- 🌱 2025.4 Our new preprint “Understanding Aha Moments: from External Observations to Internal Mechanisms” released https://arxiv.org/abs/
- 🎄2024.11 Our paper “Who Wrote This? The Key to Zero-Shot LLM-Generated Text Detection Is GECScore” was accepted by CoLING 2025
- 🎄2024.11 Our survey “A Survey on LLM-Generated Text Detection: Necessity, Methods, and Future Directions” was accepted by Computational Linguistics
- 🎄2024.10 Our paper “DetectEval: Benchmarking LLM-Generated Text Detection in Real-World Scenarios” was accepted by NeurIPS 2024 D&B Track
- 🌱2024.08 Begin my Ph.D. journey at the PRADA Lab at KAUST, under the supervision of Professor Di Wang.
- 🎄2024.07 Our paper “Model Autophagy Analysis to Explicate Self-consumption within Human-AI Interactions” was accepted by 1st Conference of Language Modeling 2024
- 🌱2024.06 I completed my Master's degree at the University of Macau ,under the supervision of Professor Derek Wong.
Services
- Reviewer for NeurIPS2025, ICML2025, ICLR 2025, AISTATS 2025, NeurIPS 2024, ARR
Visiting and Collaboration