activity
20242026
collaborators

6 papers

cs.LG2026

Causal Time Series Generation via Diffusion Models

Yutong Xia, Chang Xu, Yuxuan Liang +4

Time series generation (TSG) synthesizes realistic sequences and has achieved remarkable success. Among TSG, conditional models generate sequences given observed covariates, howeve…

cs.LG2026

Routing Channel-Patch Dependencies in Time Series Forecasting with Graph Spectral Decomposition

Dongyuan Li, Shun Zheng, Chang Xu +2

Time series forecasting has attracted significant attention in the field of AI. Previous works have revealed that the Channel-Independent (CI) strategy improves forecasting perform…

cs.LG2025

TarDiff: Target-Oriented Diffusion Guidance for Synthetic Electronic Health Record Time Series Generation

Bowen Deng, Chang Xu, Hao Li +3

Synthetic Electronic Health Record (EHR) time-series generation is crucial for advancing clinical machine learning models, as it helps address data scarcity by providing more train…

q-fin.CP2025

MarS: a Financial Market Simulation Engine Powered by Generative Foundation Model

Junjie Li, Yang Liu, Weiqing Liu +4

Generative models aim to simulate realistic effects of various actions across different contexts, from text generation to visual effects. Despite significant efforts to build real-…

cs.LG2025

TimeDP: Learning to Generate Multi-Domain Time Series with Domain Prompts

Yu-Hao Huang, Chang Xu, Yueying Wu +2

Time series generation models are crucial for applications like data augmentation and privacy preservation. Most existing time series generation models are typically designed to ge…

cs.LG2024

TimeRAF: Retrieval-Augmented Foundation model for Zero-shot Time Series Forecasting

Huanyu Zhang, Chang Xu, Yi-Fan Zhang +4

Time series forecasting plays a crucial role in data mining, driving rapid advancements across numerous industries. With the emergence of large models, time series foundation model…