Related papers: Central Dogma Transformer: Towards Mechanism-Orien…

Cell functional diversity is a significant determinant on how biological processes unfold. Most accounts of diversity involve a search for sequence or expression differences. Perhaps there are more subtle mechanisms at work. Using the…

Convolutional neural networks (CNNs) have demonstrated gratifying results at learning discriminative features. However, when applied to unseen domains, state-of-the-art models are usually prone to errors due to domain shift. After…

The hybrid architecture of convolutional neural networks (CNNs) and Transformer are very popular for medical image segmentation. However, it suffers from two challenges. First, although a CNNs branch can capture the local image features…

The Transformer translation model is based on the multi-head attention mechanism, which can be parallelized easily. The multi-head attention network performs the scaled dot-product attention function in parallel, empowering the model by…

The scattering framework offers an optimal hierarchical convolutional decomposition according to its kernels. Convolutional Neural Net (CNN) can be seen as an optimal kernel decomposition, nevertheless it requires large amount of training…

Neural Cellular Automata (NCA) represent a powerful framework for modeling biological self-organization, extending classical rule-based systems with trainable, differentiable (or evolvable) update rules that capture the adaptive…

General-purpose large language models (LLMs) are increasingly deployed in verticals such as telecommunications, where adaptation is hindered by scarce, low-information-density corpora and tight mobile/edge constraints. We propose Data…

Convolutional blocks have played a crucial role in advancing medical image segmentation by excelling in dense prediction tasks. However, their inability to effectively capture long-range dependencies has limited their performance.…

Recently, Transformers have gained significant popularity in image restoration tasks such as image super-resolution and denoising, owing to their superior performance. However, balancing performance and computational burden remains a…

Vision Transformers (ViTs) have achieved state-of-the-art performance in image classification, yet their attention mechanisms often remain opaque and exhibit dense, non-structured behaviors. In this work, we adapt our previously proposed…

Without relevant human priors, neural networks may learn uninterpretable features. We propose Dynamics of Attention for Focus Transition (DAFT) as a human prior for machine reasoning. DAFT is a novel method that regularizes attention-based…

A visual metaphor constitutes a high-order form of human creativity, employing cross-domain semantic fusion to transform abstract concepts into impactful visual rhetoric. Despite the remarkable progress of generative AI, existing models…

Recent unsupervised machine translation (UMT) systems usually employ three main principles: initialization, language modeling and iterative back-translation, though they may apply them differently. Crucially, iterative back-translation and…

End-to-end deep learning improves breast cancer classification on diffusion-weighted MR images (DWI) using a convolutional neural network (CNN) architecture. A limitation of CNN as opposed to previous model-based approaches is the…

Transformers have revolutionized nucleotide sequence analysis, yet capturing long-range dependencies remains challenging. Recent studies show that autoregressive transformers often exhibit Markovian behavior by relying on fixed-length…

We present BioLangFusion, a simple approach for integrating pre-trained DNA, mRNA, and protein language models into unified molecular representations. Motivated by the central dogma of molecular biology (information flow from gene to…

How DNA-binding proteins locate specific genomic targets remains a central challenge in molecular biology. Traditional protein-centric approaches, which rely on wet-lab experiments and visualization techniques, often lack genome-wide…

Medical foundation models pre-trained on large-scale datasets have shown powerful versatile performance. However, when adapting medical foundation models for specific medical scenarios, it remains the inevitable challenge due to the gap…

Enhancing the precision of segmenting coronary atherosclerotic plaques from CT Angiography (CTA) images is pivotal for advanced Coronary Atherosclerosis Analysis (CAA), which distinctively relies on the analysis of vessel cross-section…

Convolutional neural networks (CNN) and Transformer have wildly succeeded in multimedia applications. However, more effort needs to be made to harmonize these two architectures effectively to satisfy speech enhancement. This paper aims to…