English
Related papers

Related papers: ReMamba: Equip Mamba with Effective Long-Sequence …

200 papers

Multilingual automatic speech recognition (ASR) remains a challenging task, especially when balancing performance across high- and low-resource languages. Recent advances in sequence modeling suggest that architectures beyond Transformers…

Computation and Language · Computer Science 2025-10-24 Mohamed Nabih Ali , Daniele Falavigna , Alessio Brutti

Transformer-based models have become increasingly popular and have impacted speech-processing research owing to their exceptional performance in sequence modeling. Recently, a promising model architecture, Mamba, has emerged as a potential…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-27 Wen-Yuan Ting , Wenze Ren , Rong Chao , Hsin-Yi Lin , Yu Tsao , Fan-Gang Zeng

In scene text detection, Transformer-based methods have addressed the global feature extraction limitations inherent in traditional convolution neural network-based methods. However, most directly rely on native Transformer attention layers…

Computer Vision and Pattern Recognition · Computer Science 2025-12-09 Qiyan Zhao , Yue Yan , Da-Han Wang

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.…

State of the art foundation models such as GPT-4 perform surprisingly well at in-context learning (ICL), a variant of meta-learning concerning the learned ability to solve tasks during a neural network forward pass, exploiting contextual…

Machine Learning · Computer Science 2024-04-25 Riccardo Grazzi , Julien Siems , Simon Schrodi , Thomas Brox , Frank Hutter

Handling lengthy context is crucial for enhancing the recognition and understanding capabilities of multimodal large language models (MLLMs) in applications such as processing high-resolution images or high frame rate videos. The rise in…

Computer Vision and Pattern Recognition · Computer Science 2024-11-14 Jianing Zhou , Han Li , Shuai Zhang , Ning Xie , Ruijie Wang , Xiaohan Nie , Sheng Liu , Lingyun Wang

Image generation models have encountered challenges related to scalability and quadratic complexity, primarily due to the reliance on Transformer-based backbones. In this study, we introduce MaskMamba, a novel hybrid model that combines…

Computer Vision and Pattern Recognition · Computer Science 2024-10-01 Wenchao Chen , Liqiang Niu , Ziyao Lu , Fandong Meng , Jie Zhou

Long-short range time series forecasting is essential for predicting future trends and patterns over extended periods. While deep learning models such as Transformers have made significant strides in advancing time series forecasting, they…

Machine Learning · Computer Science 2024-09-16 Wenqing Zhang , Junming Huang , Ruotong Wang , Changsong Wei , Wenqian Huang , Yuxin Qiao

Diffusion language models (DLMs) have emerged as a promising alternative to autoregressive (AR) generation, yet their reliance on Transformer backbones limits inference efficiency due to quadratic attention or KV-cache overhead. We…

Machine Learning · Computer Science 2026-03-02 Vaibhav Singh , Oleksiy Ostapenko , Pierre-André Noël , Eugene Belilovsky , Torsten Scholak

Recent Transformer-based diffusion models have shown remarkable performance, largely attributed to the ability of the self-attention mechanism to accurately capture both global and local contexts by computing all-pair interactions among…

Computer Vision and Pattern Recognition · Computer Science 2024-09-20 Yunxiang Fu , Chaoqi Chen , Yizhou Yu

State Space Model (SSM)-based machine learning architectures have recently gained significant attention for processing sequential data. Mamba, a recent sequence-to-sequence SSM, offers competitive accuracy with superior computational…

Machine Learning · Computer Science 2025-08-15 Jiyong Kim , Jaeho Lee , Jiahao Lin , Alish Kanani , Miao Sun , Umit Y. Ogras , Jaehyun Park

State Space Models (SSMs) have recently enjoyed a rise to prominence in the field of deep learning for sequence modeling, especially as an alternative to Transformers. Their success stems from avoiding two well-known drawbacks of…

Machine Learning · Computer Science 2025-01-22 Stefano Rando , Luca Romani , Matteo Migliarini , Luca Franco , Denis Gudovskiy , Fabio Galasso

Transformers have been the most successful architecture for various speech modeling tasks, including speech separation. However, the self-attention mechanism in transformers with quadratic complexity is inefficient in computation and…

Audio and Speech Processing · Electrical Eng. & Systems 2024-05-02 Xilin Jiang , Cong Han , Nima Mesgarani

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.…

We propose Factorization Memory, an efficient recurrent neural network (RNN) architecture that achieves performance comparable to Transformer models on short-context language modeling tasks while also demonstrating superior generalization…

Computation and Language · Computer Science 2025-11-04 Lee Xiong , Maksim Tkachenko , Johanes Effendi , Ting Cai

As large language models increasingly gain popularity in real-world applications, processing extremely long contexts, often exceeding the model's pre-trained context limits, has emerged as a critical challenge. While existing approaches to…

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…

Audio and Speech Processing · Electrical Eng. & Systems 2025-07-08 Qiquan Zhang , Moran Chen , Zeyang Song , Hexin Liu , Xiangyu Zhang , Haizhou Li

State-space models (SSMs), particularly Mamba, emerge as an efficient Transformer alternative with linear complexity for long-sequence modeling. Recent empirical works demonstrate Mamba's in-context learning (ICL) capabilities competitive…

Machine Learning · Computer Science 2025-09-30 Jiarui Jiang , Wei Huang , Miao Zhang , Taiji Suzuki , Liqiang Nie

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

Log parsing is a critical standard operating procedure in software systems, enabling monitoring, anomaly detection, and failure diagnosis. However, automated log parsing remains challenging due to heterogeneous log formats, distribution…

Software Engineering · Computer Science 2026-02-10 Adam Sorrenti , Andriy Miranskyy