2 papers
cs.LG2026
ConceptTS: LLM-Guided Concept Bottlenecks for Interpretable Multivariate Time-Series Forecasting
Yichen Jiang, Yueqiao Chen, Dongyu Liu
State-of-the-art multivariate time-series forecasters can model complex temporal and cross-variable dependencies, yet their opaque representations provide limited insight into why…
cs.HC2026
ShapeTalk: Combining Natural Language and Sketch for Time-Series Pattern Querying
Guoruizhe Sun, Yueqiao Chen, Emily Guo +2
Searching for time-series segments that match user-defined patterns is important in domains such as finance, climate science, and healthcare. However, existing visual query tools o…