Xiyu Meng — accepted AI-conference papers

2026

StreamTimer: Efficient Inference for Long-Context Time Series Transformers

Xiyu Meng, Yuhan Wu, Canran Xiao, Yabo Dong, Duanqing Xu

IJCAI 2026

Time series forecasting (TSF) plays a vital role across various domains such as finance, energy, healthcare, and meteorology. Currently, most deep learning based TSF methods typically operate with a fixed lookback window. This approach comes from the high compute and memory costs of long contexts, a

Cited by 0 Scholar ↗

2025

Affirm: Interactive Mamba with Adaptive Fourier Filters for Long-term Time Series Forecasting

Yuhan Wu, Xiyu Meng, Huajin Hu, Junru Zhang, Yabo Dong, Dongming Lu

AAAI 2025technical

In long-term series forecasting (LTSF), it is imperative for models to adeptly discern and distill from historical time series data to forecast future states. Although Transformer-based models excel at capturing long-term dependencies in LTSF, their practical use is limited by issues like computatio…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗