Related papers: ML-Mamba: Efficient Multi-Modal Large Language Mod…

Prior efforts in light-weight model development mainly centered on CNN and Transformer-based designs yet faced persistent challenges. CNNs adept at local feature extraction compromise resolution while Transformers offer global reach but…

Recent years have witnessed significant advancements in light field image super-resolution (LFSR) owing to the progress of modern neural networks. However, these methods often face challenges in capturing long-range dependencies (CNN-based)…

Inspired by the excellent performance of Mamba networks, we propose a novel Deep Mamba Multi-modal Learning (DMML). It can be used to achieve the fusion of multi-modal features. We apply DMML to the field of multimedia retrieval and propose…

While transformer-based language models have driven the AI revolution thus far, their computational complexity has spurred growing interest in viable alternatives, such as structured state space sequence models (SSMs) and Selective SSMs.…

Multimodal image fusion aims to integrate information from different imaging techniques to produce a comprehensive, detail-rich single image for downstream vision tasks. Existing methods based on local convolutional neural networks (CNNs)…

Recent progress in Multimodal Large Language Models (MLLMs) has highlighted the critical roles of both the visual backbone and the underlying language model. While prior work has primarily focused on scaling these components to billions of…

In recent years, Transformers have become the de-facto architecture for long-term sequence forecasting (LTSF), but faces challenges such as quadratic complexity and permutation invariant bias. A recent model, Mamba, based on selective state…

The deployment of large language models (LLMs) in real-world clinical applications is constrained by the fundamental trade-off between computational cost and the efficiency of linear-time models. To address this, we propose an LLM-based…

In this technical report, we present Falcon Mamba 7B, a new base large language model based on the novel Mamba architecture. Falcon Mamba 7B is trained on 5.8 trillion tokens with carefully selected data mixtures. As a pure Mamba-based…

We present PlainMamba: a simple non-hierarchical state space model (SSM) designed for general visual recognition. The recent Mamba model has shown how SSMs can be highly competitive with other architectures on sequential data and initial…

Decision Transformer, a promising approach that applies Transformer architectures to reinforcement learning, relies on causal self-attention to model sequences of states, actions, and rewards. While this method has shown competitive…

Multimodal Large Language Models (MLLMs) have shown remarkable versatility in understanding diverse multimodal data and tasks. However, these capabilities come with an increased model scale. While post-training pruning reduces model size in…

Mamba is an effective state space model with linear computation complexity. It has recently shown impressive efficiency in dealing with high-resolution inputs across various vision tasks. In this paper, we reveal that the powerful Mamba…

State-Space Models (SSMs) have emerged as an efficient alternative to transformers, yet existing visual SSMs retain deeply ingrained biases from their origins in natural language processing. In this paper, we address these limitations by…

Inference with Multimodal Large Language Models (MLLMs) is slow due to their large-language-model backbone which suffers from memory bandwidth bottleneck and generates tokens auto-regressively. In this paper, we explore the application of…

Mamba has recently garnered attention as an effective backbone for vision tasks. However, its underlying mechanism in visual domains remains poorly understood. In this work, we systematically investigate Mamba's representational properties…

Video Language Models (VLMs) are crucial for generalizing across diverse tasks and using language cues to enhance learning. While transformer-based architectures have been the de facto in vision-language training, they face challenges like…

Recurrent neural networks and Transformers have recently dominated most applications in hyperspectral (HS) imaging, owing to their capability to capture long-range dependencies from spectrum sequences. However, despite the success of these…

Transformers have become the backbone of modern Large Language Models (LLMs); however, their inference overhead grows linearly with the sequence length, posing challenges for modeling long sequences. In light of this, Mamba has attracted…

Advanced long-context modeling backbone networks, such as Transformer, Conformer, and Mamba, have demonstrated state-of-the-art performance in speech enhancement. However, a systematic and comprehensive comparative study of these backbones…