English
Related papers

Related papers: Rethinking Token Reduction for State Space Models

200 papers

In multichannel speech enhancement, effectively capturing spatial and spectral information across different microphones is crucial for noise reduction. Traditional methods, such as CNN or LSTM, attempt to model the temporal dynamics of…

Audio and Speech Processing · Electrical Eng. & Systems 2025-01-15 Wenze Ren , Haibin Wu , Yi-Cheng Lin , Xuanjun Chen , Rong Chao , Kuo-Hsuan Hung , You-Jin Li , Wen-Yuan Ting , Hsin-Min Wang , Yu Tsao

Modern high-energy physics (HEP) experiments are increasingly challenged by the vast size and complexity of their datasets, particularly regarding large-scale point cloud processing and long sequences. In this study, to address these…

Machine Learning · Computer Science 2025-01-28 Cheng Jiang , Sitian Qian

Training urban spatio-temporal foundation models that generalize well across diverse regions and cities is critical for deploying urban services in unseen or data-scarce regions. Recent studies have typically focused on fusing cross-domain…

Machine Learning · Computer Science 2026-02-04 Rui An , Yifeng Zhang , Ziran Liang , Wenqi Fan , Yuxuan Liang , Xuequn Shang , Qing Li

We propose reinforcement learning (RL) strategies tailored for reasoning in large language models (LLMs) under strict memory and compute limits, with a particular focus on compatibility with LoRA fine-tuning. Building on early policy…

Machine Learning · Computer Science 2025-06-13 Alan Lee , Harry Tong

Online video super-resolution (VSR) is an important technique for many real-world video processing applications, which aims to restore the current high-resolution video frame based on temporally previous frames. Most of the existing online…

Computer Vision and Pattern Recognition · Computer Science 2026-02-25 Qiang Zhu , Xiandong Meng , Yuxian Jiang , Fan Zhang , David Bull , Shuyuan Zhu , Bing Zeng , Ronggang Wang

In recent years, visually-rich document understanding has attracted increasing attention. Transformer-based pre-trained models have become the mainstream approach, yielding significant performance gains in this field. However, the…

Computation and Language · Computer Science 2025-02-11 Pengfei Hu , Zhenrong Zhang , Jiefeng Ma , Shuhang Liu , Jun Du , Jianshu Zhang

In this paper, we analyze the computational limitations of Mamba and State-space Models (SSMs) by using the circuit complexity framework. Despite Mamba's stateful design and recent attention as a strong candidate to outperform Transformers,…

Computational Complexity · Computer Science 2025-02-21 Yifang Chen , Xiaoyu Li , Yingyu Liang , Zhenmei Shi , Zhao Song

Selective State Space Models (SSMs), notably Mamba, employ diagonal state transitions that limit both memory retention and bilinear computational capacity. We propose a factorized bilinear input modulation that augments the SSM with a…

Systems and Control · Electrical Eng. & Systems 2026-04-28 Hiroki Fujii , Masaki Yamakita

This paper examines the mathematical foundations of transformer architectures, highlighting their limitations particularly in handling long sequences. We explore prerequisite models such as Mamba, Vision Mamba (ViM), and LV-ViT that pave…

Computer Vision and Pattern Recognition · Computer Science 2024-08-06 Ricky Fang

The growing demand for efficient long-sequence modeling on edge devices has propelled widespread adoption of State Space Models (SSMs) like Mamba, due to their superior computational efficiency and scalability. As its autoregressive…

Hardware Architecture · Computer Science 2025-09-25 Linfeng Zhong , Songqiang Xu , Huifeng Wen , Tong Xie , Qingyu Guo , Yuan Wang , Meng Li

Transformers have proven effective in language modeling but are limited by high computational and memory demands that grow quadratically with input sequence length. State space models (SSMs) offer a promising alternative by reducing…

Hardware Architecture · Computer Science 2025-08-06 Dongho Yoon , Gungyu Lee , Jaewon Chang , Yunjae Lee , Dongjae Lee , Minsoo Rhu

State-space models (SSMs) are a highly expressive model class for learning patterns in time series data and for system identification. Deterministic versions of SSMs (e.g. LSTMs) proved extremely successful in modeling complex time series…

Transformer-based methods have achieved remarkable performance in event-based object detection, owing to the global modeling ability. However, they neglect the influence of non-event and noisy regions and process them uniformly, leading to…

Computer Vision and Pattern Recognition · Computer Science 2025-01-22 Nan Yang , Yang Wang , Zhanwen Liu , Meng Li , Yisheng An , Xiangmo Zhao

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…

Computer Vision and Pattern Recognition · Computer Science 2024-10-08 Hui Shen , Zhongwei Wan , Xin Wang , Mi Zhang

U-shaped architectures have long dominated the field of medical image segmentation, while Transformers are widely employed for modeling long-range dependencies. The former typically handles scale variations implicitly by aggregating…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Yanhua Zhang , Ke Zhang , Jingyu Wang , Gabriella Balestra , Samanta Rosati , Yulin Wu , Wuwei Wang , Valentina Giannini

Spoken term detection (STD) is often hindered by reliance on frame-level features and the computationally intensive DTW-based template matching, limiting its practicality. To address these challenges, we propose a novel approach that…

Audio and Speech Processing · Electrical Eng. & Systems 2024-12-24 Anup Singh , Kris Demuynck , Vipul Arora

Mamba, a State Space Model (SSM), has recently shown competitive performance to Convolutional Neural Networks (CNNs) and Transformers in Natural Language Processing and general sequence modeling. Various attempts have been made to adapt…

Computer Vision and Pattern Recognition · Computer Science 2024-08-27 Trung Dinh Quoc Dang , Huy Hoang Nguyen , Aleksei Tiulpin

Point cloud segmentation is crucial for robotic visual perception and environmental understanding, enabling applications such as robotic navigation and 3D reconstruction. However, handling the sparse and unordered nature of point cloud data…

Computer Vision and Pattern Recognition · Computer Science 2024-07-18 Tao Wang , Wei Wen , Jingzhi Zhai , Kang Xu , Haoming Luo

State space models (SSMs) have emerged as a powerful framework for modelling long-range dependencies in sequence data. Unlike traditional recurrent neural networks (RNNs) and convolutional neural networks (CNNs), SSMs offer a structured and…

Machine Learning · Computer Science 2024-10-07 Siddhanth Bhat

Mamba's recurrent state h_t is, by construction, a compressed summary of every token seen so far. This raises a tempting hypothesis: if we extract token-level outputs y_t at fixed patch boundaries, we obtain semantic sentence summaries for…

Computation and Language · Computer Science 2026-05-04 Bhagyashree Wagh , Akash Singh
‹ Prev 1 8 9 10 Next ›