English
Related papers

Related papers: Block-Recurrent Transformers

200 papers

Recent LLMs have hundreds of billions of parameters consuming vast resources. Furthermore, the so called "AI scaling law" for transformers suggests that the number of parameters must scale linearly with the size of the data. In response, we…

Computation and Language · Computer Science 2026-01-05 B. N. Kausik

Deep stacked RNNs are usually hard to train. Adding shortcut connections across different layers is a common way to ease the training of stacked networks. However, extra shortcuts make the recurrent step more complicated. To simply the…

Computation and Language · Computer Science 2017-01-04 Huijia Wu , Jiajun Zhang , Chengqing Zong

Transformer models have established new benchmarks in natural language processing; however, their increasing depth results in substantial growth in parameter counts. While existing recurrent transformer methods address this issue by…

Computation and Language · Computer Science 2025-05-27 Anthony Nguyen , Wenjun Lin

Designing a practical, low complexity, close to optimal, channel decoder for powerful algebraic codes with short to moderate block length is an open research problem. Recently it has been shown that a feed-forward neural network…

Information Theory · Computer Science 2017-02-27 Eliya Nachmani , Elad Marciano , David Burshtein , Yair Be'ery

Recurrent neural networks can learn complex transduction problems that require maintaining and actively exploiting a memory of their inputs. Such models traditionally consider memory and input-output functionalities indissolubly entangled.…

Machine Learning · Computer Science 2018-11-09 Davide Bacciu , Antonio Carta , Alessandro Sperduti

In this paper we address the question of how to render sequence-level networks better at handling structured input. We propose a machine reading simulator which processes text incrementally from left to right and performs shallow reasoning…

Computation and Language · Computer Science 2016-09-22 Jianpeng Cheng , Li Dong , Mirella Lapata

Transformers in their common form are inherently limited to operate on whole token sequences rather than on one token at a time. Consequently, their use during online inference on time-series data entails considerable redundancy due to the…

Artificial Intelligence · Computer Science 2023-06-28 Lukas Hedegaard , Arian Bakhtiarnia , Alexandros Iosifidis

Recent byte-level language models (LMs) match the performance of token-level models without relying on subword vocabularies, yet their utility is limited by slow, byte-by-byte autoregressive generation. We address this bottleneck in the…

Tools capable of automatic code generation have the potential to augment programmer's capabilities. While straightforward code retrieval is incorporated into many IDEs, an emerging area is explicit code generation. Code generation is…

Computation and Language · Computer Science 2020-12-09 Carlos Gemmell , Federico Rossetto , Jeffrey Dalton

Transformers process images and videos by flattening space and time into long token sequences. While attention and KV caching preserve past features, their memory grows with sequence length and they lack an explicit, persistent spatial…

Computer Vision and Pattern Recognition · Computer Science 2026-05-28 Kabir Swain , Sijie Han , Daniel Karl I. Weidele , Mauro Martino , Antonio Torralba

We show that a constant number of self-attention layers can efficiently simulate, and be simulated by, a constant number of communication rounds of Massively Parallel Computation. As a consequence, we show that logarithmic depth is…

Machine Learning · Computer Science 2024-02-15 Clayton Sanford , Daniel Hsu , Matus Telgarsky

While transformer models have been highly successful, they are computationally inefficient. We observe that for each layer, the full width of the layer may be needed only for a small subset of tokens inside a batch and that the "effective"…

Machine Learning · Computer Science 2024-12-19 Bartosz Wójcik , Alessio Devoto , Karol Pustelnik , Pasquale Minervini , Simone Scardapane

We propose Beam Tree Recursive Cell (BT-Cell) - a backpropagation-friendly framework to extend Recursive Neural Networks (RvNNs) with beam search for latent structure induction. We further extend this framework by proposing a relaxation of…

Machine Learning · Computer Science 2023-06-21 Jishnu Ray Chowdhury , Cornelia Caragea

Attention mechanisms have become a standard tool for sequence modeling tasks, in particular by stacking self-attention layers over the entire input sequence as in the Transformer architecture. In this work we introduce a novel attention…

Machine Learning · Computer Science 2021-06-09 Da Ju , Stephen Roller , Sainbayar Sukhbaatar , Jason Weston

Recurrent neural network is a powerful model that learns temporal patterns in sequential data. For a long time, it was believed that recurrent networks are difficult to train using simple optimizers, such as stochastic gradient descent, due…

Neural and Evolutionary Computing · Computer Science 2015-04-20 Tomas Mikolov , Armand Joulin , Sumit Chopra , Michael Mathieu , Marc'Aurelio Ranzato

In this paper, we introduce a new task for code completion that focuses on handling long code input and propose a sparse Transformer model, called LongCoder, to address this task. LongCoder employs a sliding window mechanism for…

Software Engineering · Computer Science 2023-06-27 Daya Guo , Canwen Xu , Nan Duan , Jian Yin , Julian McAuley

Effectively learning from sequential data is a longstanding goal of Artificial Intelligence, especially in the case of long sequences. From the dawn of Machine Learning, several researchers have pursued algorithms and architectures capable…

Machine Learning · Computer Science 2025-08-19 Matteo Tiezzi , Michele Casoni , Alessandro Betti , Marco Gori , Stefano Melacci

Transformer networks, driven by self-attention, are central to Large Language Models. In generative Transformers, self-attention uses cache memory to store token projections, avoiding recomputation at each time step. However, GPU-stored…

Neural and Evolutionary Computing · Computer Science 2024-11-26 Nathan Leroux , Paul-Philipp Manea , Chirag Sudarshan , Jan Finkbeiner , Sebastian Siegel , John Paul Strachan , Emre Neftci

We explore a neural network architecture that stacks a recurrent layer and a feedforward layer that is also connected to the input, and compare it to standard Elman and LSTM architectures in terms of accuracy and interpretability. When…

Neural and Evolutionary Computing · Computer Science 2020-05-29 Christian Oliva , Luis F. Lago-Fernández

Recurrent Neural Networks (RNNs) are powerful sequence modeling tools. However, when dealing with high dimensional inputs, the training of RNNs becomes computational expensive due to the large number of model parameters. This hinders RNNs…

Machine Learning · Computer Science 2018-05-23 Jinmian Ye , Linnan Wang , Guangxi Li , Di Chen , Shandian Zhe , Xinqi Chu , Zenglin Xu