Modeling multivariate time series is a well-established problem with a wide range of
applications from healthcare to financial markets. Traditional State Space Models (SSMs) …

Evaluating the contribution of individual data points to a model's prediction is critical for
interpreting model predictions and improving model performance. Existing data contribution …

In this paper, we focus on estimating the causal effect of an intervention over time on a
dynamical system. To that end, we formally define causal interventions and their effects over …

Large Language Models have demonstrated impressive performance in many pivotal web
applications such as sensor data analysis. However, since LLMs are not designed for time …

DTMamba : Dual Twin Mamba for Time Series Forecasting Page 1 DTMamba : Dual Twin
Mamba for Time Series Forecasting Zexue Wu ∗ Yifeng Gong ∗ zexue.wu@bit.edu.cn …

This work introduces a novel Text-Guided Time Series Forecasting (TGTSF) task. By
integrating textual cues, such as channel descriptions and dynamic news, TGTSF addresses …

Forecasting models are pivotal in a data-driven world with vast volumes of time series data
that appear as a compound of vast Linear and Nonlinear patterns. Recent deep time series …

Deep neural networks have significantly advanced time-series forecasting but often at the
cost of high computational requirements. Linear models, on the other hand, have …