Related papers: MambaQuant: Quantizing the Mamba Family with Varia…
With new sequence models like Mamba and xLSTM, several studies have shown that these models match or outperform the state-of-the-art in single-channel speech enhancement and audio representation learning. However, prior research has…
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…
Discrete video tokenization is essential for efficient autoregressive generative modeling due to the high dimensionality of video data. This work introduces a state-of-the-art discrete video tokenizer with two key contributions. First, we…
LLMs are seeing growing use for applications which require large context windows, and with these large context windows KV cache activations surface as the dominant contributor to memory consumption during inference. Quantization is a…
Vision-Language Models (VLMs) have enabled a variety of real-world applications. The large parameter size of VLMs brings large memory and computation overhead which poses significant challenges for deployment. Post-Training Quantization…
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…
Effective reasoning is crucial to solving complex mathematical problems. Recent large language models (LLMs) have boosted performance by scaling test-time computation through long chain-of-thought reasoning. However, transformer-based…
Mamba, a recently proposed linear-time sequence model, has attracted significant attention for its computational efficiency and strong empirical performance. However, a rigorous theoretical understanding of its underlying mechanisms remains…
Despite the remarkable quality of LLM-based text-to-speech systems, their reliance on autoregressive Transformers leads to quadratic computational complexity, which severely limits practical applications. Linear-time alternatives, notably…
Recently, quantization has been widely used for the compression and acceleration of large language models (LLMs). Due to the outliers in LLMs, it is crucial to flatten weights and activations to minimize quantization error with equally…
Recently, the Mamba architecture has demonstrated significant successes in various computer vision tasks, such as classification and segmentation. However, its application to optical flow estimation remains unexplored. In this paper, we…
Recent advancements in imitation learning, particularly with the integration of LLM techniques, are set to significantly improve robots' dexterity and adaptability. This paper proposes using Mamba, a state-of-the-art architecture with…
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…
The rapid growth of long-duration, high-definition videos has made efficient video quality assessment (VQA) a critical challenge. Existing research typically tackles this problem through two main strategies: reducing model parameters and…
In computed tomography imaging, metal implants frequently generate severe artifacts that compromise image quality and hinder diagnostic accuracy. There are three main challenges in the existing methods: the deterioration of organ and tissue…
In this effort, we propose using the Mamba for handling tabular data in personalized recommendation systems. We present the \textit{FT-Mamba} (Feature Tokenizer\,$+$\,Mamba), a novel hybrid model that replaces Transformer layers with Mamba…
Efficient evaluation of three-dimensional (3D) medical images is crucial for diagnostic and therapeutic practices in healthcare. Recent years have seen a substantial uptake in applying deep learning and computer vision to analyse and…
Cross-modal alignment is crucial for multimodal representation fusion due to the inherent heterogeneity between modalities. While Transformer-based methods have shown promising results in modeling inter-modal relationships, their quadratic…
Recent advances in deep learning have mainly relied on Transformers due to their data dependency and ability to learn at scale. The attention module in these architectures, however, exhibits quadratic time and space in input size, limiting…
Magnetic Resonance Fingerprinting (MRF) enables fast quantitative imaging by matching signal evolutions to a predefined dictionary. However, conventional dictionary matching suffers from exponential growth in computational cost and memory…