12 papers
Diff-MN: Diffusion Parameterized MoE-NCDE for Continuous Time Series Generation with Irregular Observations
Xu Zhang, Junwei Deng, Chang Xu +2
Time series generation (TSG) is widely used across domains, yet most existing methods assume regular sampling and fixed output resolutions. These assumptions are often violated in…
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…
Efficient Document Parsing via Parallel Token Prediction
Lei Li, Ze Zhao, Meng Li +6
Document parsing, as a fundamental yet crucial vision task, is being revolutionized by vision-language models (VLMs). However, the autoregressive (AR) decoding inherent to VLMs cre…
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…
OATS: Online Data Augmentation for Time Series Foundation Models
Junwei Deng, Chang Xu, Jiaqi W. Ma +5
Time Series Foundation Models (TSFMs) are a powerful paradigm for time series analysis and are often enhanced by synthetic data augmentation to improve the training data quality. E…
ChatAD: Reasoning-Enhanced Time-Series Anomaly Detection with Multi-Turn Instruction Evolution
Hui Sun, Chang Xu, Haonan Xie +7
LLM-driven Anomaly Detection (AD) helps enhance the understanding and explanatory abilities of anomalous behaviors in Time Series (TS). Existing methods face challenges of inadequa…