English
Related papers

Related papers: The Cursive Transformer

200 papers

Length Generalization is the essential capacity of autonomous agents to perform tasks in longer contexts than those encountered during training. To systematically study this feat, we test how well models can approximate the next token…

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

We explore neural painters, a generative model for brushstrokes learned from a real non-differentiable and non-deterministic painting program. We show that when training an agent to "paint" images using brushstrokes, using a differentiable…

Computer Vision and Pattern Recognition · Computer Science 2019-04-23 Reiichiro Nakano

We explore a novel way of conceptualising the task of polyphonic music transcription, using so-called invertible neural networks. Invertible models unify both discriminative and generative aspects in one function, sharing one set of…

Sound · Computer Science 2019-09-05 Rainer Kelz , Gerhard Widmer

This work proposes kernel transform learning. The idea of dictionary learning is well known; it is a synthesis formulation where a basis is learnt along with the coefficients so as to generate or synthesize the data. Transform learning is…

Computer Vision and Pattern Recognition · Computer Science 2020-08-10 Jyoti Maggu , Angshul Majumdar

Tokenisation is the first step in almost all NLP tasks, and state-of-the-art transformer-based language models all use subword tokenisation algorithms to process input text. Existing algorithms have problems, often producing tokenisations…

Computation and Language · Computer Science 2022-10-25 Edward Gow-Smith , Harish Tayyar Madabushi , Carolina Scarton , Aline Villavicencio

Deploying transformer models in practice is challenging due to their inference cost, which scales quadratically with input sequence length. To address this, we present a novel Learned Token Pruning (LTP) method which adaptively removes…

Computation and Language · Computer Science 2022-06-06 Sehoon Kim , Sheng Shen , David Thorsley , Amir Gholami , Woosuk Kwon , Joseph Hassoun , Kurt Keutzer

Convolutional Neural Networks have made their mark in various fields of computer vision in recent years. They have achieved state-of-the-art performance in the field of document analysis as well. However, CNNs require a large amount of…

Computer Vision and Pattern Recognition · Computer Science 2018-01-29 Neha Gurjar , Sebastian Sudholt , Gernot A. Fink

The adoption of Transformer-based models in natural language processing (NLP) has led to great success using a massive number of parameters. However, due to deployment constraints in edge devices, there has been a rising interest in the…

Computation and Language · Computer Science 2021-08-04 Klaudia Bałazy , Mohammadreza Banaei , Rémi Lebret , Jacek Tabor , Karl Aberer

Transformers have emerged as a powerful neural network architecture capable of tackling a wide range of learning tasks. In this work, we provide a theoretical analysis of their ability to automatically extract structure from data in an…

Machine Learning · Statistics 2025-10-29 Rodrigo Maulen-Soto , Pierre Marion , Claire Boyer

Token compression is essential for reducing the computational and memory requirements of transformer models, enabling their deployment in resource-constrained environments. In this work, we propose an efficient and hardware-compatible token…

Computer Vision and Pattern Recognition · Computer Science 2025-04-01 Junzhu Mao , Yang Shen , Jinyang Guo , Yazhou Yao , Xiansheng Hua

Transcribing struck-through, handwritten words, for example for the purpose of genetic criticism, can pose a challenge to both humans and machines, due to the obstructive properties of the superimposed strokes. This paper investigates the…

Computer Vision and Pattern Recognition · Computer Science 2022-04-04 Raphaela Heil , Ekta Vats , Anders Hast

Neural Audio Codecs, initially designed as a compression technique, have gained more attention recently for speech generation. Codec models represent each audio frame as a sequence of tokens, i.e., discrete embeddings. The discrete and…

Audio and Speech Processing · Electrical Eng. & Systems 2024-10-31 Alexander H. Liu , Qirui Wang , Yuan Gong , James Glass

Transformer-based models have been achieving state-of-the-art results in several fields of Natural Language Processing. However, its direct application to speech tasks is not trivial. The nature of this sequences carries problems such as…

Computation and Language · Computer Science 2022-05-17 Gerard Sant , Gerard I. Gállego , Belen Alastruey , Marta R. Costa-Jussà

Adapting language models to new data distributions by simple finetuning is challenging. This is due to the rigidity of their subword tokenizers, which typically remain unchanged during adaptation. This inflexibility often leads to…

Computation and Language · Computer Science 2026-05-14 Abraham Toluwase Owodunni , Orevaoghene Ahia , Sachin Kumar

Grapheme-to-phoneme (G2P) conversion is the process of converting the written form of words to their pronunciations. It has an important role for text-to-speech (TTS) synthesis and automatic speech recognition (ASR) systems. In this paper,…

Audio and Speech Processing · Electrical Eng. & Systems 2022-02-24 Chendong Zhao , Jianzong Wang , Xiaoyang Qu , Haoqian Wang , Jing Xiao

Large language models like GPT-4 exhibit emergent capabilities across general-purpose tasks, such as basic arithmetic, when trained on extensive text data, even though these tasks are not explicitly encoded by the unsupervised, next-token…

Machine Learning · Computer Science 2023-07-10 Nayoung Lee , Kartik Sreenivasan , Jason D. Lee , Kangwook Lee , Dimitris Papailiopoulos

Data representation remains a fundamental challenge in machine learning, particularly when adapting sequence-based architectures like Transformers and Large Language Models (LLMs) for structured tabular data. Existing methods often fail to…

Machine Learning · Computer Science 2025-08-05 Kayvan Karim , Hani Ragab Hassen. Hadj Batatia

Modern large language models use a fixed tokenizer to effectively compress text drawn from a source domain. However, applying the same tokenizer to a new target domain often leads to inferior compression, more costly inference, and reduced…

Computation and Language · Computer Science 2024-11-07 Zhili Feng , Tanya Marwah , Nicolo Fusi , David Alvarez-Melis , Lester Mackey

Graph Neural Networks are notorious for its memory consumption. A recent Transformer-based GNN called Graph Transformer is shown to obtain superior performances when long range dependencies exist. However, combining graph data and…

Machine Learning · Computer Science 2024-03-25 Eugene Ku