Search papers, labs, and topics across Lattice.
The paper introduces VisAnomBench, a new benchmark for time-series anomaly detection that includes natural-language rationales to facilitate VLM fine-tuning. They then develop VisAnomReasoner, a parameter-efficient VLM fine-tuned on VisAnomBench, to improve anomaly localization and interpretability. Experiments demonstrate that VisAnomReasoner significantly outperforms existing baselines on both VisAnomBench and the TSB-AD-U benchmark, showcasing strong generalization capabilities.
Forget brute-force VLMs: parameter-efficient fine-tuning with high-quality rationales unlocks surprisingly accurate and interpretable 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.
