Related papers: Scalable Autoregressive Image Generation with Mamb…

The autoregressive moving average (ARMA) model is a classical, and arguably one of the most studied approaches to model time series data. It has compelling theoretical properties and is widely used among practitioners. More recent deep…

Accurate microscopic medical image segmentation plays a crucial role in diagnosing various cancerous cells and identifying tumors. Driven by advancements in deep learning, convolutional neural networks (CNNs) and transformer-based models…

Accurate medical image segmentation demands the integration of multi-scale information, spanning from local features to global dependencies. However, it is challenging for existing methods to model long-range global information, where…

This paper proposes ControlMambaIR, a novel image restoration method designed to address perceptual challenges in image deraining, deblurring, and denoising tasks. By integrating the Mamba network architecture with the diffusion model, the…

Classifying 3D MRI images for early detection of Alzheimer's disease is a critical task in medical imaging. Traditional approaches using Convolutional Neural Networks (CNNs) and Transformers face significant challenges in this domain. CNNs,…

Accurate traffic forecasting is crucial for intelligent transportation systems, supporting effective traffic management, congestion reduction, and informed urban planning. However, traditional models often fail to adequately capture the…

Precise alignment of multi-modal images with inherent feature discrepancies poses a pivotal challenge in deformable image registration. Traditional learning-based approaches often consider registration networks as black boxes without…

With the rapid growth of the Internet of Things ecosystem, Automatic Modulation Classification (AMC) has become increasingly paramount. However, extended signal lengths offer a bounty of information, yet impede the model's adaptability,…

Hybrid Mamba-Transformer networks have recently garnered broad attention. These networks can leverage the scalability of Transformers while capitalizing on Mamba's strengths in long-context modeling and computational efficiency. However,…

Extracting robust discriminative features is a critical challenge in person re-identification (ReID). While Transformer-based methods have successfully addressed some limitations of convolutional neural networks (CNNs), such as their local…

Abnormality detection in medical imaging is a critical task requiring both high efficiency and accuracy to support effective diagnosis. While convolutional neural networks (CNNs) and Transformer-based models are widely used, both face…

Autoregressive generative models are commonly used, especially for those tasks involving sequential data. They have, however, been plagued by a slew of inherent flaws due to the intrinsic characteristics of chain-style conditional modeling…

Masked diffusion models (MDMs) have emerged as a promising approach for language modeling, yet they face a performance gap compared to autoregressive models (ARMs) and require more training iterations. In this work, we present the…

Autoregressive models (ARMs) currently hold state-of-the-art performance in likelihood-based modeling of image and audio data. Generally, neural network based ARMs are designed to allow fast inference, but sampling from these models is…

Mamba, with its selective State Space Models (SSMs), offers a more computationally efficient solution than Transformers for long-range dependency modeling. However, there is still a debate about its effectiveness in high-resolution 3D…

Recent advancements in image generation have made significant progress, yet existing models present limitations in perceiving and generating an arbitrary number of interrelated images within a broad context. This limitation becomes…

The problem of Time-series Forecasting is generally addressed by recurrent, Transformer-based and the recently proposed Mamba-based architectures. However, existing architectures generally process their input at a single temporal scale,…

Pretrained video generation models provide strong priors for robot control, but existing unified world action models still struggle to decode reliable actions without substantial robot-specific training. We attribute this limitation to a…

Attention mechanisms have been widely used to capture long-range dependencies among nodes in Graph Transformers. Bottlenecked by the quadratic computational cost, attention mechanisms fail to scale in large graphs. Recent improvements in…

Real-world data is high-dimensional: a book, image, or musical performance can easily contain hundreds of thousands of elements even after compression. However, the most commonly used autoregressive models, Transformers, are prohibitively…