相关论文: Overcoming Spectral Bias via Cross-Attention

Attention is a core component of transformer architecture, whether encoder-only, decoder-only, or encoder-decoder model. However, the standard softmax attention often produces noisy probability distribution, which can impair effective…

Parameter-efficient continual learning aims to adapt pre-trained models to sequential tasks without forgetting previously acquired knowledge. Most existing approaches treat continual learning as avoiding interference with past updates,…

Neural operators have emerged as a powerful tool for learning the mapping between infinite-dimensional parameter and solution spaces of partial differential equations (PDEs). In this work, we focus on multiscale PDEs that have important…

We propose a novel framework, Continuous_Time Attention, which infuses partial differential equations (PDEs) into the Transformer's attention mechanism to address the challenges of extremely long input sequences. Instead of relying solely…

Recent works have shown that traditional Neural Network (NN) architectures display a marked frequency bias in the learning process. Namely, the NN first learns the low-frequency features before learning the high-frequency ones. In this…

This paper presents a spectral attention-driven reinforcement learning based intelligent method for effective and efficient detection of important signals in a wideband spectrum. In the work presented in this paper, it is assumed that the…

In recent years, various applications in computer vision have achieved substantial progress based on deep learning, which has been widely used for image fusion and shown to achieve adequate performance. However, suffering from limited…

The success of vision transformers-especially for generative modeling-is limited by the quadratic cost and weak spatial inductive bias of self-attention. We propose PDE-SSM, a spatial state-space block that replaces attention with a…

The vulnerability of deep neural networks to adversarial samples has been a major impediment to their broad applications, despite their success in various fields. Recently, some works suggested that adversarially-trained models emphasize…

Breast ultrasound imaging is an important noninvasive method for early breast cancer diagnosis, but automatic benign/malignant classification remains challenging due to tumor heterogeneity, blurred boundaries, and data imbalance. To improve…

Recently, self-attention mechanisms have shown impressive performance in various NLP and CV tasks, which can help capture sequential characteristics and derive global information. In this work, we explore how to extend self-attention…

We study the problem of \emph{architecture selection} for deep learning models trained to solve partial differential equations (PDEs), asking when transformer-based architectures with learned attention outperform Fourier-domain neural…

Ensuring the robustness of deep neural networks against adversarial attacks remains a fundamental challenge in computer vision. While adversarial training (AT) has emerged as a promising defense strategy, our analysis reveals a critical…

Solving partial differential equations (PDEs) by neural networks as well as Kolmogorov-Arnold Networks (KANs), including physics-informed neural networks (PINNs), physics-informed KANs (PIKANs), and neural operators, are known to exhibit…

The complexity of scene parsing grows with the number of object and scene classes, which is higher in unrestricted open scenes. The biggest challenge is to model the spatial relation between scene elements while succeeding in identifying…

Speculative decoding (SD) is a widely adopted approach for accelerating inference in large language models (LLMs), particularly when the draft and target models are well aligned. However, state-of-the-art SD methods typically rely on…

In multi-task learning (MTL) for visual scene understanding, it is crucial to transfer useful information between multiple tasks with minimal interferences. In this paper, we propose a novel architecture that effectively transfers…

Accurate beam prediction is essential for maintaining reliable links and high spectral efficiency in dynamic low-altitude wireless networks. However, existing approaches often fail to capture the deep correlations across heterogeneous…

Cross-attention is the primary interface through which text conditions latent diffusion models, yet its step-wise multi-resolution dynamics remain under-characterized, limiting principled training-free control. We cast diffusion…

Neural operators have emerged as powerful surrogates for modeling complex physical problems. However, they suffer from spectral bias making them oblivious to high-frequency modes, which are present in multiscale physical systems. Therefore,…