English
Related papers

Related papers: Transformers are Multi-State RNNs

200 papers

Recurrent neural networks (RNNs) provide state-of-the-art performance in processing sequential data but are memory intensive to train, limiting the flexibility of RNN models which can be trained. Reversible RNNs---RNNs for which the…

Machine Learning · Computer Science 2018-10-26 Matthew MacKay , Paul Vicol , Jimmy Ba , Roger Grosse

Despite the popularity of transformers in practice, their architectures are empirically designed and neither mathematically justified nor interpretable. Moreover, as indicated by many empirical studies, some components of transformer…

Machine Learning · Computer Science 2025-06-05 Peng Wang , Yifu Lu , Yaodong Yu , Druv Pai , Qing Qu , Yi Ma

Pre-trained Transformer models like T5 and BART have advanced the state of the art on a wide range of text generation tasks. Compressing these models into smaller ones has become critically important for practical use. Common neural network…

Computation and Language · Computer Science 2023-06-06 Wangchunshu Zhou , Ronan Le Bras , Yejin Choi

This work introduces a Transformer-based image compression system. It has the flexibility to switch between the standard image reconstruction and the denoising reconstruction from a single compressed bitstream. Instead of training separate…

Image and Video Processing · Electrical Eng. & Systems 2024-02-21 Yi-Hsin Chen , Kuan-Wei Ho , Shiau-Rung Tsai , Guan-Hsun Lin , Alessandro Gnutti , Wen-Hsiao Peng , Riccardo Leonardi

Transformers have revolutionized machine learning with their simple yet effective architecture. Pre-training Transformers on massive text datasets from the Internet has led to unmatched generalization for natural language understanding…

Despite the remarkable practical success of transformer-based language models, recent work has raised concerns about their ability to perform state tracking. In particular, a growing body of literature has shown this limitation primarily…

Machine Learning · Computer Science 2026-02-23 M. Reza Ebrahimi , Michaël Defferrard , Sunny Panchal , Roland Memisevic

While Transformer models have achieved remarkable success in various domains, the effectiveness of information propagation through deep networks remains a critical challenge. Standard hidden state residuals often fail to adequately preserve…

Computation and Language · Computer Science 2025-06-10 Zhanchao Zhou , Tianyi Wu , Zhiyun Jiang , Fares Obeid , Zhenzhong Lan

Transformers achieve remarkable performance in several tasks but due to their quadratic complexity, with respect to the input's length, they are prohibitively slow for very long sequences. To address this limitation, we express the…

Machine Learning · Computer Science 2020-09-01 Angelos Katharopoulos , Apoorv Vyas , Nikolaos Pappas , François Fleuret

Transformers are ubiquitous models in the natural language processing (NLP) community and have shown impressive empirical successes in the past few years. However, little is understood about how they reason and the limits of their…

Computation and Language · Computer Science 2024-03-18 Michael Rizvi , Maude Lizaire , Clara Lacroce , Guillaume Rabusseau

Recurrent neural networks (RNNs) and transformers have been shown to be Turing-complete, but this result assumes infinite precision in their hidden representations, positional encodings for transformers, and unbounded computation time in…

Computational Complexity · Computer Science 2023-09-27 Ankur Mali , Alexander Ororbia , Daniel Kifer , Lee Giles

We introduce Neural Tensor Network States ($\nu$TNS), a variational many-body wave-function ansatz that integrates deep neural networks with tensor-network architectures. In the $\nu$TNS framework, a neural network serves as a disentangler…

Strongly Correlated Electrons · Physics 2026-03-17 Chaohui Fan , Bo Zhan , Yuntian Gu , Tong Liu , Yantao Wu , Mingpu Qin , Dingshun Lv , Tao Xiang

Since hardware resources are limited, the objective of training deep learning models is typically to maximize accuracy subject to the time and memory constraints of training and inference. We study the impact of model size in this setting,…

Computation and Language · Computer Science 2020-06-24 Zhuohan Li , Eric Wallace , Sheng Shen , Kevin Lin , Kurt Keutzer , Dan Klein , Joseph E. Gonzalez

Despite the remarkable success of Transformer-based architectures in various sequential modeling tasks, such as natural language processing, computer vision, and robotics, their ability to learn basic sequential models, like Hidden Markov…

Machine Learning · Computer Science 2024-06-07 Jiachen Hu , Qinghua Liu , Chi Jin

Compressed file formats are the corner stone of efficient data storage and transmission, yet their potential for representation learning remains largely underexplored. We introduce TEMPEST (TransformErs froM comPressed rEpreSenTations), a…

Over the last years, state-tracking tasks, particularly permutation composition, have become a testbed to understand the limits of sequence models architectures like Transformers and RNNs (linear and non-linear). However, these are often…

Machine Learning · Computer Science 2026-04-24 Julien Siems , Riccardo Grazzi , Kirill Kalinin , Hitesh Ballani , Babak Rahmani

In this paper, we present a novel transformer-based architecture for end-to-end image compression. Our architecture incorporates blocks that effectively capture local dependencies between tokens, eliminating the need for positional encoding…

Image and Video Processing · Electrical Eng. & Systems 2024-09-09 Bouzid Arezki , Fangchen Feng , Anissa Mokraoui

Disentangling the content and style in the latent space is prevalent in unpaired text style transfer. However, two major issues exist in most of the current neural models. 1) It is difficult to completely strip the style information from…

Computation and Language · Computer Science 2019-08-21 Ning Dai , Jianze Liang , Xipeng Qiu , Xuanjing Huang

We present ReadOnce Transformers, an approach to convert a transformer-based model into one that can build an information-capturing, task-independent, and compressed representation of text. The resulting representation is reusable across…

Computation and Language · Computer Science 2021-08-05 Shih-Ting Lin , Ashish Sabharwal , Tushar Khot

Transformer is a new kind of neural architecture which encodes the input data as powerful features via the attention mechanism. Basically, the visual transformers first divide the input images into several local patches and then calculate…

Computer Vision and Pattern Recognition · Computer Science 2021-10-27 Kai Han , An Xiao , Enhua Wu , Jianyuan Guo , Chunjing Xu , Yunhe Wang

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