Paper “EDAD: An Encode-then-Decompose Approach to Unsupervised Time Series Anomaly Detection on Contaminated Training Data” accepted by ICDE 2026
Two papers (“SRSNet” & “DBLoss”) accepted to NeurIPS 2025 (including one Spotlight)
Paper “TAB: Unified Benchmarking of Time Series Anomaly Detection Methods” accepted by PVLDB 2025
Papers “TSFM-Bench”, “SSD-TS”, and “DUET” accepted by SIGKDD 2025
Paper “K2VAE: A Koopman-Kalman Enhanced Variational AutoEncoder for Probabilistic Time Series Forecasting” accepted as ICML 2025 Spotlight
Paper “CATCH: Channel-Aware Multivariate Time Series Anomaly Detection via Frequency Patching” accepted by ICLR 2025
Paper “EasyTime: Time Series Forecasting Made Easy” accepted by ICDE 2025
Paper “TFB: Towards Comprehensive and Fair Benchmarking of Time Series Forecasting Methods” nominated for VLDB 2024 Best Research Paper Award
First place in Master Group of 2025 CCF Academic Show
National Scholarship recipient in both 2024 and 2025
Outstanding Reviewer for SIGKDD 2025 Research Track and Excellent Reviewer for Applied Data Science (ADS) Track
Co-created OpenTS, a leaderboard for time series analytics
Background
PhD student at School of Data Science and Engineering, East China Normal University (since Fall 2023)
Member of the Decision Intelligence Lab
Research interests include Time Series Analysis and Deep Learning
Currently working on foundation time series models and time series benchmarking
Dedicated to advancing intelligent systems that handle massive and complex temporal data in real-world domains such as finance, industry, and environment