Related papers: Dimba: Transformer-Mamba Diffusion Models

Diffusion Models have become very popular for Semantic Image Synthesis (SIS) of human faces. Nevertheless, their training and inference is computationally expensive and their computational requirements are high due to the quadratic…

In image fusion tasks, images from different sources possess distinct characteristics. This has driven the development of numerous methods to explore better ways of fusing them while preserving their respective characteristics.Mamba, as a…

Speech-driven gesture generation is an emerging domain within virtual human creation, where current methods predominantly utilize Transformer-based architectures that necessitate extensive memory and are characterized by slow inference…

Transformer, a deep neural network architecture, has long dominated the field of natural language processing and beyond. Nevertheless, the recent introduction of Mamba challenges its supremacy, sparks considerable interest among…

We propose a novel hybrid Mamba-Transformer backbone, MambaVision, specifically tailored for vision applications. Our core contribution includes redesigning the Mamba formulation to enhance its capability for efficient modeling of visual…

Magnetic Resonance Imaging (MRI) and Computed Tomography (CT) are the predominant modalities utilized in the field of medical imaging. Although MRI capture the complexity of anatomical structures with greater detail than CT, it entails a…

Expanding the long-context capabilities of Multi-modal Large Language Models~(MLLMs) is critical for advancing video understanding and high-resolution image analysis. Achieving this requires systematic improvements in model architecture,…

Transformer and its derivatives have achieved success in diverse tasks across computer vision, natural language processing, and speech processing. To reduce the complexity of computations within the multi-head self-attention mechanism in…

In this work, we empirically study Diffusion Transformers (DiTs) for text-to-image generation, focusing on architectural choices, text-conditioning strategies, and training protocols. We evaluate a range of DiT-based…

Selective state-space models (SSMs) like Mamba overcome some of the shortcomings of Transformers, such as quadratic computational complexity with sequence length and large inference-time memory requirements from the key-value cache.…

Recent 2D CNN-based domain adaptation approaches struggle with long-range dependencies due to limited receptive fields, making it difficult to adapt to target domains with significant spatial distribution changes. While transformer-based…

We propose Hymba, a family of small language models featuring a hybrid-head parallel architecture that integrates transformer attention mechanisms with state space models (SSMs) for enhanced efficiency. Attention heads provide…

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,…

Foundation models learn transferable representations, motivating growing interest in their application to wireless systems. Existing wireless foundation models are predominantly based on transformer architectures, whose quadratic…

Mamba and Vision Mamba (Vim) models have shown their potential as an alternative to methods based on Transformer architecture. This work introduces Fast Mamba for Vision (Famba-V), a cross-layer token fusion technique to enhance the…

Multi-modal image fusion integrates complementary information from different modalities to produce enhanced and informative images. Although State-Space Models, such as Mamba, are proficient in long-range modeling with linear complexity,…

Transformer-based large language models (LLMs) are increasingly being adopted in networking research to address domain-specific challenges. However, their quadratic time complexity and substantial model sizes often result in significant…

The Transformer architecture has shown a remarkable ability in modeling global relationships. However, it poses a significant computational challenge when processing high-dimensional medical images. This hinders its development and…

Referring Image Segmentation~(RIS) leveraging transformers has achieved great success on the interpretation of complex visual-language tasks. However, the quadratic computation cost makes it resource-consuming in capturing long-range…

The Mamba architecture has emerged as a promising alternative to CNNs and Transformers for image deblurring. However, its flatten-and-scan strategy often results in local pixel forgetting and channel redundancy, limiting its ability to…