相关论文: Let SSMs be ConvNets: State-space Modeling with Op…

Spiking neural networks (SNNs) take inspiration from the brain to enable energy-efficient computations. Since the advent of Transformers, SNNs have struggled to compete with artificial networks on modern sequential tasks, as they inherit…

Recent State Space Models (SSMs) such as S4, S5, and Mamba have shown remarkable computational benefits in long-range temporal dependency modeling. However, in many sequence modeling problems, the underlying process is inherently modular…

Tensors offer a natural representation for many kinds of data frequently encountered in machine learning. Images, for example, are naturally represented as third order tensors, where the modes correspond to height, width, and channels.…

State-space models (SSMs) have emerged as a powerful foundation for long-range sequence modeling, with the HiPPO framework showing that continuous-time projection operators can be used to derive stable, memory-efficient dynamical systems…

State Space Models (SSMs) have recently emerged as efficient alternatives to Transformer-Based Models (TBMs) for long-sequence processing with linear scaling, yet how contextual information flows across layers in these architectures remains…

We propose a restricted class of tensor network state, built from number-state preserving tensors, for supervised learning tasks. This class of tensor network is argued to be a natural choice for classifiers as (i) they map classical data…

Deep neural networks (DNNs) have delivered a remarkable performance in many tasks of computer vision. However, over-parameterized representations of popular architectures dramatically increase their computational complexity and storage…

State Space Models (SSMs) have emerged as an efficient alternative to the transformer architecture. Recent studies show that SSMs can match or surpass Transformers on code understanding tasks, such as code retrieval, when trained under…

Quantum machine learning (QML) is a rapidly expanding field that merges the principles of quantum computing with the techniques of machine learning. One of the powerful mathematical frameworks in this domain is tensor networks. These…

We construct parametrized isometric tensor network states -- referred to as skeletons -- that allow us to explore phases of abelian topological order and can be efficiently implemented on quantum processors. We obtain stable finite…

Tensor networks (TNs) are one of the best available tools to study many-body quantum systems. TNs are particularly suitable for one-dimensional local Hamiltonians, while their performance for generic geometries is mainly limited by two…

The deep network model, with the majority built on neural networks, has been proved to be a powerful framework to represent complex data for high performance machine learning. In recent years, more and more studies turn to nonneural network…

Deep neural state-space models (SSMs) provide a powerful tool for modeling dynamical systems solely using operational data. Typically, neural SSMs are trained using data collected from the actual system under consideration, despite the…

Learned visual compression is an important and active task in multimedia. Existing approaches have explored various CNN- and Transformer-based designs to model content distribution and eliminate redundancy, where balancing efficacy (i.e.,…

It is a challenging task to accurately perform semantic segmentation due to the complexity of real picture scenes. Many semantic segmentation methods based on traditional deep learning insufficiently captured the semantic and appearance…

The landscape of computational building blocks of efficient image restoration architectures is dominated by a combination of convolutional processing and various attention mechanisms. However, convolutional filters, while efficient, are…

Although transformer is preferred in natural language processing, some studies has only been applied to the field of medical imaging in recent years. For its long-term dependency, the transformer is expected to contribute to unconventional…

Point cloud videos capture dynamic 3D motion while reducing the effects of lighting and viewpoint variations, making them highly effective for recognizing subtle and continuous human actions. Although Selective State Space Models (SSMs)…

State Space Models (SSMs) have emerged as a compelling alternative to attention models for long-range vision tasks, offering input-dependent recurrence with linear complexity. However, most efficient SSM variants reduce computation cost by…

State space models (SSMs) have recently shown promising results on small-scale sequence and language modelling tasks, rivalling and outperforming many attention-based approaches. In this paper, we propose a multi-head state space (MH-SSM)…