Related papers: Tokenization vs. Augmentation: A Systematic Study …

Despite the advent of deep learning in computer vision, the general handwriting recognition problem is far from solved. Most existing approaches focus on handwriting datasets that have clearly written text and carefully segmented labels. In…

We introduce a new tokenizer for language models that minimizes the average tokens per character, thereby reducing the number of tokens needed to represent text during training and to generate text during inference. Our method, which we…

Tokenization is fundamental in assembly code analysis, impacting intrinsic characteristics like vocabulary size, semantic coverage, and extrinsic performance in downstream tasks. Despite its significance, tokenization in the context of…

Knowledge distillation (KD) requires sufficient data to transfer knowledge from large-scale teacher models to small-scale student models. Therefore, data augmentation has been widely used to mitigate the shortage of data under specific…

Pretrained multilingual language models are often assumed to be script-agnostic, yet their tokenizers can impose systematic costs on certain writing systems. We quantify this script tax by comparing two orthographic variants with identical…

Character-level language models obviate the need for separately trained tokenizers, but efficiency suffers from longer sequence lengths. Learning to combine character representations into tokens has made training these models more…

We introduce two data augmentation techniques, which, used with a Resnet-BiLSTM-CTC network, significantly reduce Word Error Rate (WER) and Character Error Rate (CER) beyond best-reported results on handwriting text recognition (HTR) tasks.…

We introduce a multi-scale Image Super Resolution (ISR) method building on recent advances in Visual Auto-Regressive (VAR) modeling. VAR models break image tokenization into additive, gradually increasing scales, using Residual Quantization…

Large Language Models improve with increasing amounts of high-quality training data. However, leveraging larger datasets requires balancing quality, quantity, and diversity across sources. After evaluating nine baseline methods under both…

In this paper, we focus on improving the performance of the text-dependent speaker verification system in the scenario of limited training data. The speaker verification system deep learning based text-dependent generally needs a large…

This paper addresses the persistent challenge in Keyword Spotting (KWS), a fundamental component in speech technology, regarding the acquisition of substantial labeled data for training. Given the difficulty in obtaining large quantities of…

Dynamic data selection aims to accelerate training with lossless performance. However, reducing training data inherently limits data diversity, potentially hindering generalization. While data augmentation is widely used to enhance…

The purpose of speech tokenization is to transform a speech signal into a sequence of discrete representations, serving as the foundation for speech language models (SLMs). While speech tokenization has many options, their effect on the…

Deep learning often faces the challenge of efficiently processing dynamic inputs, such as sensor data or user inputs. For example, an AI writing assistant is required to update its suggestions in real time as a document is edited.…

Lack of large, well-annotated emotional speech corpora continues to limit the performance and robustness of speech emotion recognition (SER), particularly as models grow more complex and the demand for multimodal systems increases. While…

One of the factors limiting the performance of handwritten text recognition (HTR) for stenography is the small amount of annotated training data. To alleviate the problem of data scarcity, modern HTR methods often employ data augmentation.…

The number of tokens it takes to encode parallel text in different languages is known to vary. These disparities are called token premiums. Having high token premiums leads to less throughput during training and increases costs at…

Pretrained language models (LLMs) are often constrained by their fixed tokenization schemes, leading to inefficiencies and performance limitations, particularly for multilingual or specialized applications. This tokenizer lock-in presents…

For many applications, analyzing the uncertainty of a machine learning model is indispensable. While research of uncertainty quantification (UQ) techniques is very advanced for computer vision applications, UQ methods for spatio-temporal…

Current research on the advantages and trade-offs of using characters, instead of tokenized text, as input for deep learning models, has evolved substantially. New token-free models remove the traditional tokenization step; however, their…