相关论文: SEA: State-Exchange Attention for High-Fidelity Ph…

World modelling, i.e. building a representation of the rules that govern the world so as to predict its evolution, is an essential ability for any agent interacting with the physical world. Recent applications of the Transformer…

Electromagnetic transient (EMT) simulation is a crucial tool for power system dynamic analysis because of its detailed component modeling and high simulation accuracy. However, it suffers from computational burdens for large power grids…

In this paper, robust control with sea state observer and dynamic thrust allocation is proposed for the Dynamic Positioning (DP) of an accommodation vessel in the presence of unknown hydrodynamic force variation and the input time delay. In…

Learning identifiable representations in deep generative models remains a fundamental challenge, particularly for sequential data with regime-switching dynamics. Existing approaches establish identifiability under restrictive assumptions,…

Time series forecasting has made significant advances, including with Transformer-based models. The attention mechanism in Transformer effectively captures temporal dependencies by attending to all past inputs simultaneously. However, its…

Recently, data-driven models such as deep neural networks have shown to be promising tools for modelling and state inference in soft robots. However, voluminous amounts of data are necessary for deep models to perform effectively, which…

Attention networks have successfully boosted the performance in various vision problems. Previous works lay emphasis on designing a new attention module and individually plug them into the networks. Our paper proposes a novel-and-simple…

Channel State Information (CSI) Feedback plays a crucial role in achieving higher gains through beamforming. However, for a massive MIMO system, this feedback overhead is huge and grows linearly with the number of antennas. To reduce the…

Large Language Models (LLMs) based on transformers achieve cutting-edge results on a variety of applications. However, their enormous size and processing requirements hinder deployment on constrained resources. To enhance efficiency,…

Arbitrary artistic style transfer is a research area that combines rational academic study with emotive artistic creation. It aims to create a new image from a content image according to a target artistic style, maintaining the content's…

The Transformer architecture has significantly advanced deep learning, particularly in natural language processing, by effectively managing long-range dependencies. However, as the demand for understanding complex relationships grows,…

While Large Language Models and their underlying Transformer architecture are remarkably efficient, they do not reflect how our brain processes and learns a diversity of cognitive tasks such as language, nor how it leverages working memory.…

Accurate fault detection and localization in electrical distribution systems is crucial, especially with the increasing integration of distributed energy resources (DERs), which inject greater variability and complexity into grid…

Vehicular platooning promises transformative improvements in transportation efficiency and safety through the coordination of multi-vehicle formations enabled by Vehicle-to-Everything (V2X) communication. However, the distributed nature of…

Attention within windows has been widely explored in vision transformers to balance the performance, computation complexity, and memory footprint. However, current models adopt a hand-crafted fixed-size window design, which restricts their…

Fueled by recent advances of self-supervised models, pre-trained speech representations proved effective for the downstream speech emotion recognition (SER) task. Most prior works mainly focus on exploiting pre-trained representations and…

Modeling the parser state is key to good performance in transition-based parsing. Recurrent Neural Networks considerably improved the performance of transition-based systems by modelling the global state, e.g. stack-LSTM parsers, or local…

Multi-dimensional time series data, such as matrix and tensor-variate time series, are increasingly prevalent in fields such as economics, finance, and climate science. Traditional Transformer models, though adept with sequential data, do…

The Transformer architecture has become the foundation of modern deep learning, yet its core self-attention mechanism suffers from quadratic computational complexity and lacks grounding in biological neural computation. We propose Selective…

Multimodal Large Language Models (MLLMs) have serious security vulnerabilities.While safety alignment using multimodal datasets consisting of text and data of additional modalities can effectively enhance MLLM's security, it is costly to…