HYVE cuts LLM token usage on machine data by 50-90% using database-style hybrid views and a request-scoped datastore while maintaining or improving quality on tasks like anomaly detection and chart generation.
Anomaly detection: A survey
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
A problem-oriented taxonomy groups anomaly detection metrics into six dimensions and experiments show that some popular ones like NAB and Point-Adjust fail to resist random-score inflation.
MADRI detects anomalies in human-robot pick-and-place tasks by reconstructing multimodal feature vectors from video, internal sensors, and scene graphs, with multimodal versions outperforming vision-only on a custom dataset.
citing papers explorer
-
HYVE: Hybrid Views for LLM Context Engineering over Machine Data
HYVE cuts LLM token usage on machine data by 50-90% using database-style hybrid views and a request-scoped datastore while maintaining or improving quality on tasks like anomaly detection and chart generation.
-
A Problem-Oriented Taxonomy of Evaluation Metrics for Time Series Anomaly Detection
A problem-oriented taxonomy groups anomaly detection metrics into six dimensions and experiments show that some popular ones like NAB and Point-Adjust fail to resist random-score inflation.
-
Multimodal Anomaly Detection for Human-Robot Interaction
MADRI detects anomalies in human-robot pick-and-place tasks by reconstructing multimodal feature vectors from video, internal sensors, and scene graphs, with multimodal versions outperforming vision-only on a custom dataset.