activity
20242026
collaborators

28 papers

cs.LG2026

Enhancing Irregular Time Series Forecasting with Continuous-Time Modeling Framework

Tianen Shen, Zhengyu Li, Yutong Li +4

The paper introduces WrapFlow, a framework that directly tokenizes irregular multivariate time‑series observations into continuous‑time tokens and uses a Transformer with a simulat…

cs.LG2026

CATCH: Channel-Aware multivariate Time Series Anomaly Detection via Frequency Patching

Xingjian Wu, Xiangfei Qiu, Zhengyu Li +5

Anomaly detection in multivariate time series is challenging as heterogeneous subsequence anomalies may occur. Reconstruction-based methods, which focus on learning normal patterns…

cs.LG2026

Adaptive Oscillatory-State Alignment for Time Series Forecasting

Zhangyao Song, Chaofeng Qu, Chao Zha +3

Long-term time series forecasting benefits from inductive biases that expose recurring temporal structure. Existing periodic forecasting methods typically model recurrence through…

cs.LG2026

Differentiable Mixture-of-Agents Incentivizes Swarm Intelligence of Large Language Models

Xingjian Wu, Junkai Lu, Siyu Yan +4

Recent advances in Large Language Models (LLMs) have catalyzed the development of multi-agent systems (MAS) for complex reasoning tasks. However, existing MAS typically rely on pre…

cs.LG2026

DAG: A Dual Correlation Network for Time Series Forecasting with Exogenous Variables

Xiangfei Qiu, Yuhan Zhu, Zhengyu Li +3

Time series forecasting is essential in various domains. Compared to relying solely on endogenous variables (i.e., target variables), considering exogenous variables (i.e., covaria…

cs.LG2026

Hermes: A Multi-Scale Spatial-Temporal Hypergraph Network for Stock Time Series Forecasting

Xiangfei Qiu, Liu Yang, Xiangyu Xu +9

Time series forecasting occurs in a range of financial applications providing essential decision-making support to investors, regulatory institutions, and analysts. Unlike multivar…