English
Related papers

Related papers: MEGABYTE: Predicting Million-byte Sequences with M…

200 papers

Language models with recurrent depth, also referred to as universal or looped when considering transformers, are defined by the capacity to increase their computation through the repetition of layers. Recent efforts in pretraining have…

Machine Learning · Computer Science 2025-10-17 Jonas Geiping , Xinyu Yang , Guinan Su

Sequence classification is essential in NLP for understanding and categorizing language patterns in tasks like sentiment analysis, intent detection, and topic classification. Transformer-based models, despite achieving state-of-the-art…

Computation and Language · Computer Science 2025-09-30 Hongbo Liu , Jia Xu

We introduce a new beam search decoder that is fully differentiable, making it possible to optimize at training time through the inference procedure. Our decoder allows us to combine models which operate at different granularities (e.g.…

Computation and Language · Computer Science 2019-02-19 Ronan Collobert , Awni Hannun , Gabriel Synnaeve

Current methods which compress multisets at an optimal rate have computational complexity that scales linearly with alphabet size, making them too slow to be practical in many real-world settings. We show how to convert a compression…

Information Theory · Computer Science 2023-02-28 Daniel Severo , James Townsend , Ashish Khisti , Alireza Makhzani , Karen Ullrich

Deep learning-based speech enhancement (SE) models have achieved impressive performance in the past decade. Numerous advanced architectures have been designed to deliver state-of-the-art performance; however, their scalability potential…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-25 Wangyou Zhang , Kohei Saijo , Jee-weon Jung , Chenda Li , Shinji Watanabe , Yanmin Qian

This paper addresses the challenge of creating a neural architecture for very long sequences that requires constant time for processing new information at each time step. Our approach, Associative Recurrent Memory Transformer (ARMT), is…

Computation and Language · Computer Science 2025-02-17 Ivan Rodkin , Yuri Kuratov , Aydar Bulatov , Mikhail Burtsev

Transformer-based time series foundation models face a fundamental trade-off in choice of tokenization: point-wise embeddings preserve temporal fidelity but scale poorly with sequence length, whereas fixed-length patching improves…

Artificial Intelligence · Computer Science 2026-03-13 Sravan Kumar Ankireddy , Nikita Seleznev , Nam H. Nguyen , Yulun Wu , Senthil Kumar , Furong Huang , C. Bayan Bruss

We propose SutraNets, a novel method for neural probabilistic forecasting of long-sequence time series. SutraNets use an autoregressive generative model to factorize the likelihood of long sequences into products of conditional…

Machine Learning · Computer Science 2023-12-25 Shane Bergsma , Timothy Zeyl , Lei Guo

Modern neural sequence generation models are built to either generate tokens step-by-step from scratch or (iteratively) modify a sequence of tokens bounded by a fixed length. In this work, we develop Levenshtein Transformer, a new partially…

Computation and Language · Computer Science 2019-10-29 Jiatao Gu , Changhan Wang , Jake Zhao

Autoregressive generative models of images tend to be biased towards capturing local structure, and as a result they often produce samples which are lacking in terms of large-scale coherence. To address this, we propose two methods to learn…

Computer Vision and Pattern Recognition · Computer Science 2019-10-09 Jeffrey De Fauw , Sander Dieleman , Karen Simonyan

The objective of dense material segmentation is to identify the material categories for every image pixel. Recent studies adopt image patches to extract material features. Although the trained networks can improve the segmentation…

Computer Vision and Pattern Recognition · Computer Science 2024-02-29 Yuwen Heng , Srinandan Dasmahapatra , Hansung Kim

Transformers have shown dominant performance across a range of domains including language and vision. However, their computational cost grows quadratically with the sequence length, making their usage prohibitive for resource-constrained…

Computation and Language · Computer Science 2023-10-24 Yinghan Long , Sayeed Shafayet Chowdhury , Kaushik Roy

Modern language models are trained almost exclusively on token sequences produced by a fixed tokenizer, an external lossless compressor often over UTF-8 byte sequences, thereby coupling the model to that compressor. This work introduces…

Computation and Language · Computer Science 2026-05-15 Lin Zheng , Xinyu Li , Qian Liu , Xiachong Feng , Lingpeng Kong

Transformer-based models show their effectiveness across multiple domains and tasks. The self-attention allows to combine information from all sequence elements into context-aware representations. However, global and local information has…

Computation and Language · Computer Science 2022-12-09 Aydar Bulatov , Yuri Kuratov , Mikhail S. Burtsev

Aiming at improving the performance of existing detection algorithms developed for different applications, we propose a region regression-based multi-stage class-agnostic detection pipeline, whereby the existing algorithms are employed for…

Computer Vision and Pattern Recognition · Computer Science 2016-07-19 Wei Li , Matthias Breier , Dorit Merhof

Decoding in a Transformer based language model is inherently sequential as a token's embedding needs to pass through all the layers in the network before the generation of the next token can begin. In this work, we propose a new…

Machine Learning · Computer Science 2025-08-27 Dylan Cutler , Arun Kandoor , Nishanth Dikkala , Nikunj Saunshi , Xin Wang , Rina Panigrahy

Models such as Sequence-to-Sequence and Image-to-Sequence are widely used in real world applications. While the ability of these neural architectures to produce variable-length outputs makes them extremely effective for problems like…

Machine Learning · Computer Science 2019-04-30 Chenglong Wang , Rudy Bunel , Krishnamurthy Dvijotham , Po-Sen Huang , Edward Grefenstette , Pushmeet Kohli

Digital forensic investigations often face significant challenges when recovering fragmented multimedia files that lack file system metadata. While traditional file carving relies on signatures and discriminative deep learning models for…

Computer Vision and Pattern Recognition · Computer Science 2026-04-14 Jaewon Lee , Md Eimran Hossain Eimon , Avinash Srinivasan , Hari Kalva

Recurrent Neural Networks were, until recently, one of the best ways to capture the timely dependencies in sequences. However, with the introduction of the Transformer, it has been proven that an architecture with only attention-mechanisms…

Machine Learning · Computer Science 2021-08-19 Radostin Cholakov , Todor Kolev

We present a new approach to modeling sequential data: the deep equilibrium model (DEQ). Motivated by an observation that the hidden layers of many existing deep sequence models converge towards some fixed point, we propose the DEQ approach…

Machine Learning · Computer Science 2019-10-30 Shaojie Bai , J. Zico Kolter , Vladlen Koltun
‹ Prev 1 8 9 10 Next ›