Wenxiao Wang

发表论文 12 篇 · 总被引 171 次 · h-index 5

代表论文

• Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks (2023 · International Conference on Learning Representations · 被引 109)
• Can AI-Generated Text be Reliably Detected? Stress Testing AI Text Detectors Under Various Attacks (2025 · Trans. Mach. Learn. Res. · 被引 37)
• Spuriosity Rankings: Sorting Data to Measure and Mitigate Biases (2022 · Neural Information Processing Systems · 被引 19)
• Tool Preferences in Agentic LLMs are Unreliable (2025 · Conference on Empirical Methods in Natural Language Processing · 被引 13)
• Maestro: Joint Graph & Config Optimization for Reliable AI Agents (2025 · arXiv.org · 被引 8)
• Your LLM Agents are Temporally Blind: The Misalignment Between Tool Use Decisions and Human Time Perception (2025 · Annual Meeting of the Association for Computational Linguistics · 被引 6)