Scholar
Wenxiao Wang
Google Scholar ID: hn0u5VgAAAAJ
RELAI.ai
Citations & Impact
Citations
2,024
H-index
11
i10-index
11
Publications
19
Co-authors
0
Publications
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
- Published multiple papers including 'Towards Reliable Agentic LLMs' (Ph.D. Dissertation, 2025), 'DyePack: Provably Flagging Test Set Contamination in LLMs Using Backdoors' (EMNLP 2025), 'Tool Preferences in Agentic LLMs are Unreliable' (EMNLP 2025), 'Can AI-Generated Text be Reliably Detected?' (TMLR 2025), 'Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks' (ICLR 2024), 'DRSM: De-Randomized Smoothing on Malware Classifier Providing Certified Robustness' (ICLR 2024), 'Temporal Robustness against Data Poisoning' (NeurIPS 2023), 'Spuriosity Rankings: Sorting Data for Spurious Correlation Robustness' (NeurIPS 2023), 'Lethal Dose Conjecture on Data Poisoning' (NeurIPS 2022), 'Improved Certified Defenses against Data Poisoning with (Deterministic) Finite Aggregation' (ICML 2022), 'On Feature Decorrelation in Self-Supervised Learning' (ICCV 2021).
Research Experience
- Research intern at Sony AI (summer 2023), working with Dr. Weiming Zhuang and Dr. Lingjuan Lyu; research intern at Bytedance (summer 2022), working with Dr. Linjie Yang, Dr. Heng Wang, and Dr. Yu Tian; research assistant at IIIS, Tsinghua University (2020-2021), working with Prof. Hang Zhao; visiting student researcher at UC Berkeley (2019), working with Dr. Xinyun Chen, Prof. Ruoxi Jia, and Prof. Dawn Song; intern at Bytedance AI Lab (2018), working with Dr. Yi He and Prof. Lei Li.
Education
- Obtained a Ph.D. in Computer Science from the University of Maryland in 2025, advised by Prof. Soheil Feizi; B.S. in Computer Science from Yao Class, Tsinghua University in 2020.
Background
- Currently the Head of AI at RELAI, Inc. Research interests include reliable AI agents and privacy-preserving machine learning.
Co-authors