English
Related papers

Related papers: Fixed-Point RNNs: Interpolating from Diagonal to D…

200 papers

Recurrent neural networks have gained widespread use in modeling sequential data. Learning long-term dependencies using these models remains difficult though, due to exploding or vanishing gradients. In this paper, we draw connections…

Machine Learning · Statistics 2019-02-27 Bo Chang , Minmin Chen , Eldad Haber , Ed H. Chi

Transformers are highly parallel but are limited to computations in the TC$^0$ complexity class, excluding tasks such as entity tracking and code execution that provably require greater expressive power. Motivated by this limitation, we…

Machine Learning · Computer Science 2026-05-15 Mayank Mishra , Shawn Tan , Ion Stoica , Joseph Gonzalez , Tri Dao

Graph Neural Networks (GNNs) have shown promising potential in graph representation learning. The majority of GNNs define a local message-passing mechanism, propagating information over the graph by stacking multiple layers. These methods,…

Machine Learning · Computer Science 2024-02-20 Ali Behrouz , Farnoosh Hashemi

Recurrent Neural Networks (RNNs) have been widely used in processing natural language tasks and achieve huge success. Traditional RNNs usually treat each token in a sentence uniformly and equally. However, this may miss the rich semantic…

Computation and Language · Computer Science 2018-11-14 Chang Xu , Weiran Huang , Hongwei Wang , Gang Wang , Tie-Yan Liu

Recurrent neural networks (RNNs) have shown the ability to improve scene parsing through capturing long-range dependencies among image units. In this paper, we propose dense RNNs for scene labeling by exploring various long-range semantic…

Computer Vision and Pattern Recognition · Computer Science 2018-11-13 Heng Fan , Peng Chu , Longin Jan Latecki , Haibin Ling

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

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

Linear State Space Models (SSMs) offer remarkable performance gains in efficient sequence modeling, with constant inference-time computation and memory complexity. Recent advances, such as Mamba, further enhance SSMs with input-dependent…

Machine Learning · Computer Science 2025-06-24 Zheng Zhan , Liliang Ren , Shuohang Wang , Liyuan Liu , Yang Liu , Yeyun Gong , Yanzhi Wang , Yelong Shen

Recurrent neural networks have shown excellent performance in many applications, however they require increased complexity in hardware or software based implementations. The hardware complexity can be much lowered by minimizing the…

Machine Learning · Computer Science 2016-09-28 Sungho Shin , Kyuyeon Hwang , Wonyong Sung

The Mamba layer offers an efficient selective state space model (SSM) that is highly effective in modeling multiple domains, including NLP, long-range sequence processing, and computer vision. Selective SSMs are viewed as dual models, in…

Machine Learning · Computer Science 2024-04-02 Ameen Ali , Itamar Zimerman , Lior Wolf

Softmax attention is the principle backbone of foundation models for various artificial intelligence applications, yet its quadratic complexity in sequence length can limit its inference throughput in long-context settings. To address this…

Machine Learning · Computer Science 2024-12-10 Jerome Sieber , Carmen Amo Alonso , Alexandre Didier , Melanie N. Zeilinger , Antonio Orvieto

Attention mechanisms have been widely used to capture long-range dependencies among nodes in Graph Transformers. Bottlenecked by the quadratic computational cost, attention mechanisms fail to scale in large graphs. Recent improvements in…

Machine Learning · Computer Science 2024-02-02 Chloe Wang , Oleksii Tsepa , Jun Ma , Bo Wang

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…

Sequence modeling plays a vital role across various domains, with recurrent neural networks being historically the predominant method of performing these tasks. However, the emergence of transformers has altered this paradigm due to their…

Recurrent Neural Networks (RNNs) are a class of machine learning algorithms used for applications with time-series and sequential data. Recently, there has been a strong interest in executing RNNs on embedded devices. However, difficulties…

Neural and Evolutionary Computing · Computer Science 2020-03-23 Nesma M. Rezk , Madhura Purnaprajna , Tomas Nordström , Zain Ul-Abdin

Recurrent neural networks (RNNs) are capable of learning features and long term dependencies from sequential and time-series data. The RNNs have a stack of non-linear units where at least one connection between units forms a directed cycle.…

Neural and Evolutionary Computing · Computer Science 2018-02-26 Hojjat Salehinejad , Sharan Sankar , Joseph Barfett , Errol Colak , Shahrokh Valaee

Linear transformers have emerged as a subquadratic-time alternative to softmax attention and have garnered significant interest due to their fixed-size recurrent state that lowers inference cost. However, their original formulation suffers…

Computation and Language · Computer Science 2024-05-13 Jean Mercat , Igor Vasiljevic , Sedrick Keh , Kushal Arora , Achal Dave , Adrien Gaidon , Thomas Kollar

Recurrent Neural Networks (RNNs) are among the most successful machine learning models for sequence modelling, but tend to suffer from an exponential increase in the number of parameters when dealing with large multidimensional data. To…

Machine Learning · Computer Science 2021-05-12 Yao Lei Xu , Danilo P. Mandic

Sequence modeling is currently dominated by causal transformer architectures that use softmax self-attention. Although widely adopted, transformers require scaling memory and compute linearly during inference. A recent stream of work…

A new breed of gated-linear recurrent neural networks has reached state-of-the-art performance on a range of sequence modeling problems. Such models naturally handle long sequences efficiently, as the cost of processing a new input is…

Machine Learning · Computer Science 2024-06-13 Maciej Pióro , Maciej Wołczyk , Razvan Pascanu , Johannes von Oswald , João Sacramento