时序异常检测终于有了可解释的小模型方案，做工业监控或运维分析的团队可以直接用VisAnomReasoner替代大模型，精度更高、成本更低，建议点开看具体微调方法。
研究者发现现有视觉语言模型在时序异常检测任务上表现不佳，主要原因是公开数据集缺乏自然语言解释，难以微调模型。为此，他们构建了VisAnomBench基准，从公开时序数据中筛选并利用多个大模型生成高质量异常解释。基于此微调出参数高效的VisAnomReasoner模型，在VisAnomBench上精度和F1分别提升至少21.23和23.87个百分点，在TSB-AD-U基准上也展现出强泛化能力。这项工作让小型VLM在时序异常检测中变得可靠且可解释。
Tiny but Trusted: Efficient Vision-Language Reasoning for Time-Series Anomaly Detection
Recent advances in Vision-Language Models (VLMs) have achieved impressive performance across many tasks, yet prior studies report unsatisfactory performance when applying large language or multimodal models to finding abnormal patterns in sequential data. Public anomaly detection benchmarks typically provide interval annotations but not natural-language rationales, making it difficult to fine-tune VLMs to produce grounded, interpretable decisions. To address this gap, we construct VisAnomBench, a curated benchmark built from public time-series datasets and augmented with high-quality anomaly explanations selected from multiple large VLMs using fine-grained, task-specific rewards. Through fine-tuning on this benchmark, we develop VisAnomReasoner, a parameter-efficient VLM for time-series anomaly detection. Experimental results on VisAnomBench show that VisAnomReasoner achieves more accurate anomaly localization and consistently outperforms all baselines, with improvements of at least 21.23 and 23.87 percentage points in precision and F1, respectively. Additional experiments on the TSB-AD-U benchmark demonstrate strong cross-benchmark generalization, with VisAnomReasoner improving precision and F1 by 9.57 and 13.39 percentage points, respectively.