Method · Distribution and feature matching
UniTSC
One Batch Is Enough: A Unified Dataset Condensation Framework for General Time Series Analysis
Wei Shao, Ziquan Fang, Zheqi Lu, Yongfeng Su, Yuzhu Wang, Yunjun Gao
ICML 2026 · first public 2026-01
In one paragraph
UniTSC argues that prior time-series condensation methods are task-specific (optimized for one downstream task such as forecasting and performing poorly on others such as imputation), and proposes a task-invariant condensation framework that jointly captures temporal, spectral and topological properties of the data so the same condensed set generalizes across multiple time-series analysis tasks.
Where it sits
- Distribution and feature matching (Surrogate matching)
- Setting: Time series and spatio-temporal data
BibTeX (generated; prefer the venue's official entry)
@article{shao2026batch,
title = {One Batch Is Enough: A Unified Dataset Condensation Framework for General Time Series Analysis},
author = {Wei Shao and Ziquan Fang and Zheqi Lu and Yongfeng Su and Yuzhu Wang and Yunjun Gao},
journal = {ICML 2026},
year = {2026}
}Nearby in Distribution and feature matching
RAHA — Rank-Aware Hyperbolic Alignment for Vision-Language Dataset Distillation
Jongoh Jeong, Sun-Kyung Lee, Kuk-Jin Yoon · ECCV 2026notableVision–languagepaper ↗code ↗
MDM — Multimodal Distribution Matching for Vision-Language Dataset Distillation
Jongoh Jeong, Hoyong Kwon, Minseok Kim et al. · CVPR 2026notableVision–languagepaper ↗code ↗
Harmonic Dataset Distillation for Time Series Forecasting
Seungha Hong, Sanghwan Jang, Wonbin Kweon et al. · AAAI 2026notableTime seriespaper ↗
Algorithmic Guarantees for Distilling Supervised and Offline RL Datasets
Aaryan Gupta, Rishi Saket, Aravindan Raghuveer · ICLR 2026notableOther datapaper ↗