Related papers: CausalMamba: Scalable Conditional State Space Mode…

Topological deep learning has emerged as a powerful paradigm for modeling higher-order relational structures beyond pairwise interactions that standard graph neural networks fail to capture. While combinatorial complexes (CCs) offer a…

Causal reasoning is often challenging with spatial data, particularly when handling high-dimensional inputs. To address this, we propose a neural network (NN) based framework integrated with an approximate Gaussian process to manage spatial…

Causal representation learning algorithms discover lower-dimensional representations of data that admit a decipherable interpretation of cause and effect; as achieving such interpretable representations is challenging, many causal learning…

In clinical practice, the robustness of deep learning models for multimodal brain tumor segmentation is severely compromised by incomplete MRI data. This vulnerability stems primarily from modality bias, where models exploit spurious…

Recent learned image compression (LIC) leverages Mamba-style state-space models (SSMs) for global receptive fields with linear complexity. However, the standard Mamba adopts content-agnostic, predefined raster (or multi-directional) scans…

Recently, the Mamba architecture based on state space models has demonstrated remarkable performance in a series of natural language processing tasks and has been rapidly applied to remote sensing change detection (CD) tasks. However, most…

The accelerated MRI reconstruction poses a challenging ill-posed inverse problem due to the significant undersampling in k-space. Deep neural networks, such as CNNs and ViTs, have shown substantial performance improvements for this task…

Modern deep learning models excel at pattern recognition but remain fundamentally limited by their reliance on spurious correlations, leading to poor generalization and a demand for massive datasets. We argue that a key ingredient for…

Accurate detection of cardiac abnormalities from electrocardiogram recordings is regarded as essential for clinical diagnostics and decision support. Traditional deep learning models such as residual networks and transformer architectures…

One of the central elements of any causal inference is an object called structural causal model (SCM), which represents a collection of mechanisms and exogenous sources of random variation of the system under investigation (Pearl, 2000). An…

Reconstructing degraded images is a critical task in image processing. Although CNN and Transformer-based models are prevalent in this field, they exhibit inherent limitations, such as inadequate long-range dependency modeling and high…

Robust characterization of dynamic causal interactions in multivariate biomedical signals is essential for advancing computational and algorithmic methods in biomedical imaging. Conventional approaches, such as Dynamic Bayesian Networks…

State-Space Models (SSMs) have emerged as efficient alternatives to transformers for sequential data tasks, offering linear or near-linear scalability with sequence length, making them ideal for long-sequence applications in NLP, vision,…

Sequence models like Transformers and RNNs often overallocate attention to irrelevant context, leading to noisy intermediate representations. This degrades LLM capabilities by promoting hallucinations, weakening long-range and retrieval…

Perceptual image compression focuses on preserving high visual quality under low-bitrate constraints. Most existing approaches to perceptual compression leverage the strong generative capabilities of generative adversarial networks or…

Despite the groundbreaking advancements made by large language models (LLMs), hallucination remains a critical bottleneck for their deployment in high-stakes domains. Existing classification-based methods mainly rely on static and passive…

Medical image segmentation plays an important role in various clinical applications; however, existing deep learning models face trade-offs between efficiency and accuracy. Convolutional Neural Networks (CNNs) capture local details well but…

Two-view correspondence learning aims to discern true and false correspondences between image pairs by recognizing their underlying different information. Previous methods either treat the information equally or require the explicit storage…

Video anomaly detection (VAD) has been extensively researched due to its potential for intelligent video systems. However, most existing methods based on CNNs and transformers still suffer from substantial computational burdens and have…

Human activity recognition (HAR) from inertial sensors is essential for ubiquitous computing, mobile health, and ambient intelligence. Conventional deep models such as Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs),…