SRT: Super-Resolution for Time Series via Disentangled Rectified Flow
SRT: 基于解缠校正流的时间序列超分辨率
机构 * Bytedance(字节跳动)
AI总结 提出SRT框架,通过解缠校正流将低分辨率时间序列重建为高分辨率,分解趋势与季节成分,利用隐式神经表示对齐分辨率,并引入跨分辨率注意力机制生成细节。
Comments Accepted to the International Conference on Learning Representations (ICLR) 2026
Journal ref The Fourteenth International Conference on Learning Representations (ICLR 2026)