English
Related papers

Related papers: Characterizing Mamba's Selective Memory using Auto…

200 papers

Foundation models, now powering most of the exciting applications in deep learning, are almost universally based on the Transformer architecture and its core attention module. Many subquadratic-time architectures such as linear attention,…

Machine Learning · Computer Science 2024-06-03 Albert Gu , Tri Dao

Large language models (LLMs) have advanced significantly due to the attention mechanism, but their quadratic complexity and linear memory demands limit their performance on long-context tasks. Recently, researchers introduced Mamba, an…

Computation and Language · Computer Science 2024-10-22 Wangjie You , Zecheng Tang , Juntao Li , Lili Yao , Min Zhang

With the explosive growth of data, long-sequence modeling has become increasingly important in tasks such as natural language processing and bioinformatics. However, existing methods face inherent trade-offs between efficiency and memory.…

Machine Learning · Computer Science 2025-10-07 Youjin Wang , Yangjingyi Chen , Jiahao Yan , Jiaxuan Lu , Xiao Sun

Recent advancements in recurrent architectures, such as Mamba and RWKV, have showcased strong language capabilities. Unlike transformer-based models, these architectures encode all contextual information into a fixed-size state, leading to…

Computation and Language · Computer Science 2026-01-14 Yingfa Chen , Xinrong Zhang , Shengding Hu , Xu Han , Zhiyuan Liu , Maosong Sun

Recent advancements in State Space Models (SSMs) have attracted significant interest, particularly in models optimized for parallel training and handling long-range dependencies. Architectures like Mamba have scaled to billions of…

Machine Learning · Computer Science 2024-10-22 Zheng Zhan , Yushu Wu , Zhenglun Kong , Changdi Yang , Yifan Gong , Xuan Shen , Xue Lin , Pu Zhao , Yanzhi Wang

Token-free language models learn directly from raw bytes and remove the inductive bias of subword tokenization. Operating on bytes, however, results in significantly longer sequences. In this setting, standard autoregressive Transformers…

Computation and Language · Computer Science 2024-08-13 Junxiong Wang , Tushaar Gangavarapu , Jing Nathan Yan , Alexander M. Rush

State space models (SSMs), such as Mamba, have emerged as an efficient alternative to transformers for long-context sequence modeling. However, despite their growing adoption, SSMs lack the interpretability tools that have been crucial for…

Computation and Language · Computer Science 2025-02-26 Hugo Pitorro , Marcos Treviso

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 space models (SSMs) have emerged as an efficient alternative to Transformer models for language modeling, offering linear computational complexity and constant memory usage as context length increases. However, despite their…

Computation and Language · Computer Science 2025-04-23 Zhifan Ye , Kejing Xia , Yonggan Fu , Xin Dong , Jihoon Hong , Xiangchi Yuan , Shizhe Diao , Jan Kautz , Pavlo Molchanov , Yingyan Celine Lin

Long-range dependency is one of the most desired properties of recent sequence models such as state-space models (particularly Mamba) and transformer models. New model architectures are being actively developed and benchmarked for…

Machine Learning · Computer Science 2025-09-05 Cong Ma , Kayvan Najarian

Vision Mambas (ViMs) achieve remarkable success with sub-quadratic complexity, but their efficiency remains constrained by quadratic token scaling with image resolution. While existing methods address token redundancy, they overlook ViMs'…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Yan Wen , Peng Ye , Lin Zhang , Baopu Li , Jiakang Yuan , Yaoxin Yang , Tao Chen

Modern large language models are built on sequence modeling via next-token prediction. While the Transformer remains the dominant architecture for sequence modeling, its quadratic decoding complexity in sequence length poses a major…

Machine Learning · Computer Science 2024-10-03 Bo Liu , Rui Wang , Lemeng Wu , Yihao Feng , Peter Stone , Qiang Liu

Structured State Space Models (SSMs) have emerged as a transformative paradigm in sequence modeling, addressing critical limitations of Recurrent Neural Networks (RNNs) and Transformers, namely, vanishing gradients, sequential computation…

Current automatic speech recognition systems struggle with modeling long speech sequences due to high quadratic complexity of Transformer-based models. Selective state space models such as Mamba has performed well on long-sequence modeling…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-30 Xiaoxue Gao , Nancy F. Chen

Recent advances in sequence modeling have introduced selective SSMs as promising alternatives to Transformer architectures, offering theoretical computational efficiency and sequence processing advantages. A comprehensive understanding of…

Machine Learning · Computer Science 2025-12-01 Abdullah Al Asif , Mobina Kashaniyan , Sixing Yu , Juan Pablo Muñoz , Ali Jannesari

Recently, the state space model (SSM) represented by Mamba has shown remarkable performance in long-term sequence modeling tasks, including speech enhancement. However, due to substantial differences in sub-band features, applying the same…

Sound · Computer Science 2025-02-25 Jizhen Li , Weiping Tu , Yuhong Yang , Xinmeng Xu , Yiqun Zhang , Yanzhen Ren

Transformers dominate NLP and IR; but their inference inefficiencies and challenges in extrapolating to longer contexts have sparked interest in alternative model architectures. Among these, state space models (SSMs) like Mamba offer…

Computation and Language · Computer Science 2025-04-23 Zhichao Xu , Jinghua Yan , Ashim Gupta , Vivek Srikumar

Large language models (LLMs) face a daunting challenge due to the excessive computational and memory requirements of the commonly used Transformer architecture. While state space model (SSM) is a new type of foundational network…

Computation and Language · Computer Science 2024-03-06 Wei He , Kai Han , Yehui Tang , Chengcheng Wang , Yujie Yang , Tianyu Guo , Yunhe Wang

State-space models (SSMs) offer a promising architecture for sequence modeling, providing an alternative to Transformers by replacing expensive self-attention with linear recurrences. In this paper, we propose a simple yet effective trick…

Machine Learning · Computer Science 2025-05-28 Woomin Song , Jihoon Tack , Sangwoo Mo , Seunghyuk Oh , Jinwoo Shin

We study memory in state-space language models using primacy and recency effects as behavioral tools to uncover how information is retained and forgotten over time. Applying structured recall tasks to the Mamba architecture, we observe a…

Computation and Language · Computer Science 2025-06-19 Muhammad Cendekia Airlangga , Hilal AlQuabeh , Munachiso S Nwadike , Kentaro Inui
‹ Prev 1 2 3 10 Next ›