6 papers
Olivia: Harmonizing Time Series Foundation Models with Power Spectral Density
Jingru Fei, Kun Yi, Alex Xing Wang +3
Time series foundation models rely on large-scale pretraining over diverse datasets across domains, yet their heterogeneity in temporal patterns could hinder the effectiveness of t…
Improving Prediction Certainty Estimation for Reliable Early Exiting via Null Space Projection
Jianing He, Qi Zhang, Duoqian Miao +4
Early exiting has demonstrated great potential in accelerating the inference of pre-trained language models (PLMs) by enabling easy samples to exit at shallow layers, eliminating t…
Amplifier: Bringing Attention to Neglected Low-Energy Components in Time Series Forecasting
Jingru Fei, Kun Yi, Wei Fan +2
We propose an energy amplification technique to address the issue that existing models easily overlook low-energy components in time series forecasting. This technique comprises an…
MedGNN: Towards Multi-resolution Spatiotemporal Graph Learning for Medical Time Series Classification
Wei Fan, Jingru Fei, Dingyu Guo +5
Medical time series has been playing a vital role in real-world healthcare systems as valuable information in monitoring health conditions of patients. Accurate classification for…
IN-Flow: Instance Normalization Flow for Non-stationary Time Series Forecasting
Wei Fan, Shun Zheng, Pengyang Wang +5
Due to the non-stationarity of time series, the distribution shift problem largely hinders the performance of time series forecasting. Existing solutions either rely on using certa…
Wills Aligner: Multi-Subject Collaborative Brain Visual Decoding
Guangyin Bao, Qi Zhang, Zixuan Gong +6
Decoding visual information from human brain activity has seen remarkable advancements in recent research. However, the diversity in cortical parcellation and fMRI patterns across…