EUVIMEDEUVIMED entdecken
Crossref

ALARM: Automated MLLM-Based Anomaly Detection in Complex-Environment Monitoring with Uncertainty Quantification

Congjing Zhang, Ryan Feng Lin, Xinyi Zhao, Pei Guo, Wei Li, Lin Chen, Chaoyue Zhao, Shuai Huang

INFORMS Journal on Data Science · 05.03.2026

DOI: 10.1287/ijds.2025.0107 ↗

Kurz gefasst

Fachartikel in der Zeitschrift INFORMS Journal on Data Science, online erschienen am 05.03.2026. Verfasst von Congjing Zhang und 7 weiteren Autor:innen. Die Arbeit nennt 82 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The advance of large language models (LLMs) has greatly stimulated research interest in developing multimodal LLM (MLLM)-based visual anomaly detection (VAD) algorithms that can be deployed in complex environments. The challenge is that, in these complex environments, the anomalies are sometimes highly contextual and also ambiguous, and thereby, uncertainty quantification (UQ) is a crucial capacity for an MLLM-based VAD system to succeed. In this paper, we introduce our UQ-supported MLLM-based VAD framework called automated MLLM-based anomaly detection in complex-environment monitoring with UQ (ALARM). ALARM integrates UQ with quality-assurance techniques like reasoning chain, self-reflection, and MLLM ensemble for robust and accurate performance and is designed based on a rigorous probabilistic inference pipeline and computational process. Extensive empirical evaluations are conducted using the real-world smart-home benchmark data and wound image classification data, which shows ALARM’s superior performance and its generic applicability across different domains for reliable decision making. History: Yu Ding and Ningyuan Chen served as senior editors for this article. Funding: This work was supported in part by a grant from Amazon. Data Ethics & Reproducibility Note: The code capsule is available at https://github.com/RancyZ/ALARM/tree/main and in the e-Companion to this article (available at https://doi.org/10.1287/ijds.2025.0107 ).

Zitieren

APA

Zhang, C., Lin, R. F., Zhao, X., Guo, P., Li, W., Chen, L., Zhao, C., & Huang, S. (2026). ALARM: Automated MLLM-Based Anomaly Detection in Complex-Environment Monitoring with Uncertainty Quantification. INFORMS Journal on Data Science. https://doi.org/10.1287/ijds.2025.0107

Vancouver

Zhang C, Lin RF, Zhao X, Guo P, Li W, Chen L, et al. ALARM: Automated MLLM-Based Anomaly Detection in Complex-Environment Monitoring with Uncertainty Quantification. INFORMS Journal on Data Science. 2026. doi:10.1287/ijds.2025.0107

BibTeX
@article{Zhang2026,
  author = {Zhang, Congjing and Lin, Ryan Feng and Zhao, Xinyi and Guo, Pei and Li, Wei and Chen, Lin and Zhao, Chaoyue and Huang, Shuai},
  title = {ALARM: Automated MLLM-Based Anomaly Detection in Complex-Environment Monitoring with Uncertainty Quantification},
  journal = {INFORMS Journal on Data Science},
  year = {2026},
  doi = {10.1287/ijds.2025.0107}
}
Kostenlos starten →