Publications

LogRules: Enhancing Log Analysis Capability of Large Language Models through Rules

Currently, large language models (LLMs) have achieved impressive performance in natural language processing tasks. However, LLMs still …

Xin Huang, Ting Zhang, Wen Zhao

LogRules: Enhancing Log Analysis Capability of Large Language Models through Rules

Math-PUMA: Progressive Upward Multimodal Alignment to Enhance Mathematical Reasoning

Multimodal Large Language Models (MLLMs) excel in solving text-based mathematical problems, but they struggle with mathematical …

Wenwen Zhuang, Xin Huang, Xiantao Zhang, Jin Zeng

Math-PUMA: Progressive Upward Multimodal Alignment to Enhance Mathematical Reasoning

LogContrast: A Weakly Supervised Anomaly Detection Method Leveraging Contrastive Learning

We propose a novel log-based anomaly detection method that leverages weakly supervised contrastive learning, named LogContrast. …

Ting Zhang, Xin Huang, Wen Zhao, Guozhao Mo, Shaohuang Bian

LogContrast: A Weakly Supervised Anomaly Detection Method Leveraging Contrastive Learning

LogPrompt: A Log-based Anomaly Detection Framework Using Prompts

Log data are widely used in anomaly detection tasks of software system. At present, log anomaly detection methods based on deep …

Ting Zhang, Xin Huang, Wen Zhao, Shaohuang Bian, Peng Du

LogPrompt: A Log-based Anomaly Detection Framework Using Prompts

Secure Semantic Communication Model for Black-Box Attack Challenge Under Metaverse

The Metaverse is the post-reality universe, a perpetual and persistent multiuser environment merging physical reality with digital …

Chang Li, Liang Zeng, Xin Huang, Xiaqing Miao, Shuai Wang