English
Related papers

Related papers: MambaQuant: Quantizing the Mamba Family with Varia…

200 papers

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…

Sound · Computer Science 2026-01-22 Nikolai Lund Kühne , Jesper Jensen , Jan Østergaard , Zheng-Hua Tan

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…

Image and Video Processing · Electrical Eng. & Systems 2024-03-07 Jiarun Liu , Hao Yang , Hong-Yu Zhou , Yan Xi , Lequan Yu , Yizhou Yu , Yong Liang , Guangming Shi , Shaoting Zhang , Hairong Zheng , Shanshan Wang

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…

Computer Vision and Pattern Recognition · Computer Science 2025-07-08 Dawit Mureja Argaw , Xian Liu , Joon Son Chung , Ming-Yu Liu , Fitsum Reda

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…

Machine Learning · Computer Science 2025-05-30 Coleman Hooper , Sehoon Kim , Hiva Mohammadzadeh , Michael W. Mahoney , Yakun Sophia Shao , Kurt Keutzer , Amir Gholami

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…

Computer Vision and Pattern Recognition · Computer Science 2025-03-24 Shiyao Li , Yingchun Hu , Xuefei Ning , Xihui Liu , Ke Hong , Xiaotao Jia , Xiuhong Li , Yaqi Yan , Pei Ran , Guohao Dai , Shengen Yan , Huazhong Yang , Yu Wang

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…

Signal Processing · Electrical Eng. & Systems 2026-03-30 Tomer Raviv , Nir Shlezinger

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…

Machine Learning · Computer Science 2025-09-10 Junxiong Wang , Wen-Ding Li , Daniele Paliotta , Daniel Ritter , Alexander M. Rush , Tri Dao

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…

Machine Learning · Computer Science 2026-02-13 Junsoo Oh , Wei Huang , Taiji Suzuki

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…

Audio and Speech Processing · Electrical Eng. & Systems 2026-03-16 Tan Dat Nguyen , Sangmin Bae , Joon Son Chung , Ji-Hoon Kim

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…

Computation and Language · Computer Science 2025-08-12 Yuxuan Sun , Ruikang Liu , Haoli Bai , Han Bao , Kang Zhao , Yuening Li , Jiaxin Hu , Xianzhi Yu , Lu Hou , Chun Yuan , Xin Jiang , Wulong Liu , Jun Yao

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…

Computer Vision and Pattern Recognition · Computer Science 2025-08-19 Juntian Du , Zhihu Zhou , Runzhe Zhang , Yuan Sun , Pinyi Chen , Keji Mao

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…

Robotics · Computer Science 2024-09-26 Toshiaki Tsuji

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…

Computer Vision and Pattern Recognition · Computer Science 2025-12-02 Hu Gao , Xiaoning Lei , Xichen Xu , Depeng Dang , Lizhuang Ma

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…

Computer Vision and Pattern Recognition · Computer Science 2025-04-23 Yachun Mi , Yu Li , Weicheng Meng , Chaofeng Chen , Chen Hui , Shaohui Liu

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…

Computer Vision and Pattern Recognition · Computer Science 2026-04-09 Weikai Qu , Sijun Liang , Xianfeng Li , Cheng Pan , An Yan , Ahmed Elazab , Shanzhou Niu , Dong Zeng , Xiang Wan , Changmiao Wang

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…

Information Retrieval · Computer Science 2024-09-27 Andrew Starnes , Clayton Webster

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…

Computer Vision and Pattern Recognition · Computer Science 2025-03-07 Wei Dai , Jun Liu

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…

Computer Vision and Pattern Recognition · Computer Science 2024-12-03 Yan Li , Yifei Xing , Xiangyuan Lan , Xin Li , Haifeng Chen , Dongmei Jiang

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…

Machine Learning · Computer Science 2024-07-25 Ali Behrouz , Michele Santacatterina , Ramin Zabih

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…

Image and Video Processing · Electrical Eng. & Systems 2025-07-08 Tianyi Ding , Hongli Chen , Yang Gao , Zhuang Xiong , Feng Liu , Martijn A. Cloos , Hongfu Sun