Shifeng XIE bio photo

Selected Publications

Peer-reviewed journal and conference papers

  • CauKer: Classification Time Series Foundation Models Can Be Pretrained on Synthetic Data.

    Shifeng Xie, Vasilii Feofanov, Jianfeng Zhang, Themis Palpanas, and Ievgen Redko. ICLR 2026. Paper

  • Mantis: Lightweight Foundation Model for Time Series Classification.

    Vasilii Feofanov, Songkang Wen, Shifeng Xie, et al. ICML 2026. Paper

  • The Initialization Determines Whether In-Context Learning Is Gradient Descent.

    Shifeng Xie, Rui Yuan, Simone Rossi, and Thomas Hannagan. TMLR 2025. Paper

  • Subgraph Gaussian Embedding Contrast for Self-Supervised Graph Representation Learning.

    Shifeng Xie, Aref Einizade, and Jhony H. Giraldo. ECML-PKDD 2025. Paper

  • FTUnet: Feature Transferred U-Net for Single HDR Image Reconstruction.

    Shifeng Xie, Yi Liu, and Wenjing Shuai. ACM Multimedia Asia 2023 (oral). Paper

  • Feasibility Study of Intelligent Healthcare Based on Digital Twin and Data Mining.

    Shifeng Xie, Shuang Zhu, and J. Dai. CISAI 2021. Paper

First-author preprints and workshop papers

  • Tabby: An Open Pretraining Recipe for Time Series Foundation Models.

    Shifeng Xie et al. Technical report, arXiv 2026. Preprint

  • Post-Training in Time Series Foundation Models: A Unifying Framework.

    Shifeng Xie et al. Preprint, arXiv 2026. Preprint

  • TSFMAudit: Data Contamination Auditing in Forecasting Time Series Foundation Models.

    Hongkai Li and Shifeng Xie (equal contribution) et al. Preprint, arXiv 2026. Preprint

  • Rethinking Zero-Shot Time Series Classification: From Task-specific Classifiers to In-Context Inference.

    Juntao Fang and Shifeng Xie (equal contribution) et al. Preprint, arXiv 2026. Preprint

  • Time Series Foundation Models Improve LLM Decisions: A Case Study in Stock Trading. Shifeng Xie and Ziwei Li (equal contribution) et al. ICLR 2026 Workshop on Time Series in the Age of Large Models. Paper

  • Variational Graph Contrastive Learning. Shifeng Xie and Jhony H. Giraldo. NeurIPS 2024 Workshop on Self-Supervised Learning. Paper