2 papers
cs.LG2026
KALEIDO: Input-Space Adaptation of a Vision Model for Time-Series Forecasting Through Gated Fold Geometries
Xiangyu Shi, Qinghua Liu, Sam Heshmati +1
Time-series foundation models buy zero-shot forecasting with large temporal corpora; a vision model needs none, since a natural image implicitly embeds the patterns a forecaster mu…
cs.LG2025
MLLM4TS: Leveraging Vision and Multimodal Language Models for General Time-Series Analysis
Qinghua Liu, Sam Heshmati, Zheda Mai +3
Effective analysis of time series data presents significant challenges due to the complex temporal dependencies and cross-channel interactions in multivariate data. Inspired by the…