Time series, characterized by a sequence of data points arranged in a discrete-time order,
are ubiquitous in real-world applications. Different from other modalities, time series present …

As a core branch of financial forecasting, stock forecasting plays a crucial role for financial
analysts, investors, and policymakers in managing risks and optimizing investment …

Foundation models, now powering most of the exciting applications in deep learning, are
almost universally based on the Transformer architecture and its core attention module …

Designing computationally efficient network architectures remains an ongoing necessity in
computer vision. In this paper, we adapt Mamba, a state-space language model, into …

Convolutional Neural Networks (CNNs) and Transformers have been the most popular
architectures for biomedical image segmentation, but both of them have limited ability to …

While Transformers have been the main architecture behind deep learning's success in
language modeling, state-space models (SSMs) such as Mamba have recently been shown …

Abstract Recurrent Neural Networks (RNNs) offer fast inference on long sequences but are
hard to optimize and slow to train. Deep state-space models (SSMs) have recently been …

Recent years have seen significant advancements in image restoration, largely attributed to
the development of modern deep neural networks, such as CNNs and Transformers …

State space models (SSMs) have demonstrated state-of-the-art sequence modeling
performance in some modalities, but underperform attention in language modeling …

Transformers have become one of the foundational architectures in point cloud analysis
tasks due to their excellent global modeling ability. However, the attention mechanism has …