Jiachen Fu(付嘉晨)

Jiachen Fu(付嘉晨)

LLMs, VLMs, Multimodal AI, Trustworthy AI

DetectAnyLLM: Towards Generalizable and Robust Detection of Machine-Generated Text Across Domains and Models

Published in ACM International Conference on Multimedia (ACM MM 2025, CCF-A), 2025

DetectAnyLLM addresses the challenge of detecting machine-generated text in a generalizable and robust manner across different domains and LLM families.

Key Contributions:

  • A novel optimization strategy that reduces computation cost while improving performance by ~70% relative to previous SOTA methods.
  • A comprehensive benchmark dataset providing robust evaluation across diverse domains and models.

Venue: ACM MM 2025 (CCF-A), Oral Presentation

[arXiv]

Recommended citation: Fu, J., Guo, C., & Li, C. (2025). DetectAnyLLM: Towards Generalizable and Robust Detection of Machine-Generated Text Across Domains and Models. ACM MM 2025. Oral.
Download Paper