English
Related papers

Related papers: Rethinking the long-range dependency in Mamba/SSM …

200 papers

Recently, recurrent models based on linear state space models (SSMs) have shown promising performance in language modeling (LM), competititve with transformers. However, there is little understanding of the in-principle abilities of such…

Computation and Language · Computer Science 2025-12-15 Yash Sarrof , Yana Veitsman , Michael Hahn

Structured state space models (SSMs) have recently emerged as a promising foundation for sequence modeling, with Mamba-based architectures demonstrating strong performance through input-dependent state transitions, albeit at considerable…

Machine Learning · Computer Science 2026-05-28 Hassan Saadatmand , Geoffrey I. Webb , Hamid Rezatofighi , Mahsa Salehi

State Space Models (SSMs) have emerged as promising alternatives to attention mechanisms, with the Mamba architecture demonstrating impressive performance and linear complexity for processing long sequences. However, the fundamental…

Machine Learning · Computer Science 2026-01-22 Tianyi Chen , Pengxiao Lin , Zhiwei Wang , Zhi-Qin John Xu

Dynamic graph embedding has emerged as an important technique for modeling complex time-evolving networks across diverse domains. While transformer-based models have shown promise in capturing long-range dependencies in temporal graph data,…

Machine Learning · Computer Science 2025-05-13 Ashish Parmanand Pandey , Alan John Varghese , Sarang Patil , Mengjia Xu

Existing deraining Transformers employ self-attention mechanisms with fixed-range windows or along channel dimensions, limiting the exploitation of non-local receptive fields. In response to this issue, we introduce a novel dual-branch…

Computer Vision and Pattern Recognition · Computer Science 2024-09-04 Shangquan Sun , Wenqi Ren , Juxiang Zhou , Jianhou Gan , Rui Wang , Xiaochun Cao

While the conditional sequence modeling with the transformer architecture has demonstrated its effectiveness in dealing with offline reinforcement learning (RL) tasks, it is struggle to handle out-of-distribution states and actions.…

Machine Learning · Computer Science 2025-01-23 Qi Lv , Xiang Deng , Gongwei Chen , Michael Yu Wang , Liqiang Nie

Large pre-trained models have achieved outstanding results in sequence modeling. The Transformer block and its attention mechanism have been the main drivers of the success of these models. Recently, alternative architectures, such as…

Machine Learning · Computer Science 2025-01-29 J. Pablo Muñoz , Jinjie Yuan , Nilesh Jain

State space models (SSMs) have emerged as an efficient alternative to transformer-based models, offering linear complexity that scales better than transformers. One of the latest advances in SSMs, Mamba, introduces a selective scan…

Machine Learning · Computer Science 2025-03-03 Junpeng Wang , Chin-Chia Michael Yeh , Uday Singh Saini , Mahashweta Das

In recent years, there has been a growing interest in integrating linear state-space models (SSM) in deep neural network architectures of foundation models. This is exemplified by the recent success of Mamba, showing better performance than…

Systems and Control · Electrical Eng. & Systems 2024-03-26 Carmen Amo Alonso , Jerome Sieber , Melanie N. Zeilinger

Recent State Space Models (SSM), especially Mamba, have demonstrated impressive performance in visual modeling and possess superior model efficiency. However, the application of Mamba to visual tasks suffers inferior performance due to…

Computer Vision and Pattern Recognition · Computer Science 2025-05-20 Fei Xie , Jiahao Nie , Yujin Tang , Wenkang Zhang , Hongshen Zhao

Modern multivariate time series forecasting primarily relies on two architectures: the Transformer with attention mechanism and Mamba. In natural language processing, an approach has been used that combines local window attention for…

Machine Learning · Computer Science 2025-09-26 Itay Katav , Aryeh Kontorovich

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

State Space Models (SSMs)-most notably RNNs-have historically played a central role in sequential modeling. Although attention mechanisms such as Transformers have since dominated due to their ability to model global context, their…

Computer Vision and Pattern Recognition · Computer Science 2025-10-02 Hyun-kyu Ko , Youbin Kim , Jihyeon Park , Dongheok Park , Gyeongjin Kang , Wonjun Cho , Hyung Yi , Eunbyung Park

Transformer models have achieved superior performance in various natural language processing tasks. However, the quadratic computational cost of the attention mechanism limits its practicality for long sequences. There are existing…

Computation and Language · Computer Science 2022-12-19 Simiao Zuo , Xiaodong Liu , Jian Jiao , Denis Charles , Eren Manavoglu , Tuo Zhao , Jianfeng Gao

Transformers have widely adopted attention networks for sequence mixing and MLPs for channel mixing, playing a pivotal role in achieving breakthroughs across domains. However, recent literature highlights issues with attention networks,…

Computer Vision and Pattern Recognition · Computer Science 2024-04-26 Badri N. Patro , Vijay S. Agneeswaran

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

Transformers have become dominant in large-scale deep learning tasks across various domains, including text, 2D and 3D vision. However, the quadratic complexity of their attention mechanism limits their efficiency as the sequence length…

Computer Vision and Pattern Recognition · Computer Science 2024-11-04 Nursena Köprücü , Destiny Okpekpe , Antonio Orvieto

Scaling inference-time compute has emerged as an important driver of LLM performance, making inference efficiency a central focus of model design alongside model quality. While the current Transformer-based models deliver strong model…

Machine Learning · Computer Science 2026-03-17 Aakash Lahoti , Kevin Y. Li , Berlin Chen , Caitlin Wang , Aviv Bick , J. Zico Kolter , Tri Dao , Albert Gu

Selective State-Space Models (SSMs) such as Mamba have emerged as an alternative architecture to self-attention based transformers in sequence modeling tasks. Recent works have demonstrated the use of transformers in some filtering and…

Systems and Control · Electrical Eng. & Systems 2026-04-28 Alex Tang , M. Emrullah Ildiz , Batin Kurt , Samet Oymak , Necmiye Ozay

State Space Models (SSMs) have emerged as a promising alternative to the popular transformer-based models and have been increasingly gaining attention. Compared to transformers, SSMs excel at tasks with sequential data or longer contexts,…

Machine Learning · Computer Science 2025-03-17 Xingtai Lv , Youbang Sun , Kaiyan Zhang , Shang Qu , Xuekai Zhu , Yuchen Fan , Yi Wu , Ermo Hua , Xinwei Long , Ning Ding , Bowen Zhou