Cheng Wang

I'm a final-year undergraduate student from National University of Singapore (NUS). I am broadly interested in Trustworthy AI and LLM Reasoning. I am fortunate to work closely with Prof. Bryan Hooi and Prof. Tat-Seng Chua from NUS, Prof. Tianwei Zhang from NTU, Prof. Junxian He from HKUST, Prof. Muhao Chen from UC Davis, and Prof. Kai-Wei Chang from UCLA.

My primary research interests include:

  • Trustworthy AI: Hallucination Detection & Adversarial Robustness.
  • AI Reasoning: Enhancing reasoning ability of LLMs.
  • LLM Applications: Autonomous agents & RAG systems.

Email  /  Google Scholar  /  LinkedIn  /  Github

Looking for Fall 2026 PhD opportunities on Trustworthy AI and LLM Reasoning, feel free to contact!
🔥 News
  • [2025.06] Our paper GuardReasoner-VL is accepted to ICML 2025 R2-FM Workshop!
  • [2025.04] Our survey on LRMs Safety is on arxiv now, check out the paper and repo!
  • [2025.01] Our paper is accepted to NAACL 2025 Main Conference.
  • [2025.01] I started my internship at Tiktok as an Algorithm Engineer Intern.
  • [2024.11] Our paper is accepted to COLING 2025.
📑 Publications

* denotes equal contribution, see full list in Google Scholar.

2025
survey
A Sanity Check on Probing Classifiers of LLMs for Malicious Input Detection
Cheng Wang*, Zeming Wei*, Qin Liu, Wenxuan Zhou, Muhao Chen
Under Review, 2025

survey
Taming Extreme Tokens: Covariance-Aware GRPO with Gaussian-Kernel Advantage Reweighting
Cheng Wang, Qin Liu, Wenxuan Zhou, Muhao Chen
Under Review, 2025

survey
When Audio and Text Disagree: Benchmarking Text Bias in Large Audio-Language Models under Cross-Modal Inconsistencies
Cheng Wang, Gelei Deng, Xianglin Yang, Tianwei Zhang
Under Review, 2025

survey
Mitigating Hallucinations in Large Vision-Language Models without Performance Degradation
Xingyu Zhu, Junfeng Fang, Xinfeng Li, Cheng Wang, Shuo Wang, Beier Zhu, Xiangnan He
Under Review, 2025

survey
GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning
Yue Liu, Shengfang Zhai, Mingzhe Du, Yulin Chen, Tri Cao, Hongcheng Gao, Cheng Wang, Xinfeng Li, Kun Wang, Junfeng Fang, Jiaheng Zhang, Bryan Hooi
ICML 2025 R2-FM Workshop, 2025
Paper / Code
survey
Safety in Large Reasoning Models: A Survey
Cheng Wang*, Yue Liu, Baolong Bi, Duzhen Zhang, Zhongzhi Li, Junfeng Fang, Bryan Hooi
Under Review, 2025
Paper / GitHub
DIGA
Tricking Retrievers with Influential Tokens: An Efficient Black-Box Corpus Poisoning Attack
Cheng Wang, Yiwei Wang, Yujun Cai, Bryan Hooi
NAACL 2025 Main Track
Paper
con-recall
Con-ReCall: Detecting Pre-training Data in LLMs via Contrastive Decoding
Cheng Wang, Yiwei Wang, Bryan Hooi, Yujun Cai, Nanyun Peng, Kai-Wei Chang
COLING 2025
Paper
🎓 Education
nus National University of Singapore (NUS)
Period: 2022 - Present
Major: Computer Science & Math
💼 Professional & Industry Experience
tiktok Tiktok | Singapore
Algorithm Engineer Intern
Period: Jan 2025 - June 2025
nus National University of Singapore | Singapore
Teaching Assistant, Introduction to AI and Machine Learning
Period: Jan 2024 - May 2024

Template is from Jon Barron. Last update: Aug 2025