Related papers: Tokenization vs. Augmentation: A Systematic Study …
Recent advances in generative models, such as diffusion models, have made generating high-quality synthetic images widely accessible. Prior works have shown that training on synthetic images improves many perception tasks, such as image…
Handwritten Text Recognition (HTR) is crucial for document digitization, but handwritten data can contain user-identifiable features, like unique writing styles, posing privacy risks. Regulations such as the ``right to be forgotten''…
Background & Objective: Biomedical text data are increasingly available for research. Tokenization is an initial step in many biomedical text mining pipelines. Tokenization is the process of parsing an input biomedical sentence (represented…
RNN-Transducer (RNN-T) is a widely adopted architecture in speech recognition, integrating acoustic and language modeling in an end-to-end framework. However, the RNN-T predictor tends to over-rely on consecutive word dependencies in…
Subword regularization, used widely in NLP, improves model performance by reducing the dependency on exact tokenizations, augmenting the training corpus, and exposing the model to more unique contexts during training. BPE and MaxMatch, two…
Subword tokenization introduces a computational layer in language models where many distinct token sequences decode to the same surface form and preserve meaning, yet induce different internal computations. Despite this non-uniqueness,…
Token compression techniques have recently emerged as powerful tools for accelerating Vision Transformer (ViT) inference in computer vision. Due to the quadratic computational complexity with respect to the token sequence length, these…
Accurate interpretation and visualization of human instructions are crucial for text-to-image (T2I) synthesis. However, current models struggle to capture semantic variations from word order changes, and existing evaluations, relying on…
Token-based text-to-speech (TTS) models have emerged as a promising avenue for generating natural and realistic speech, yet they grapple with low pronunciation accuracy, speaking style and timbre inconsistency, and a substantial need for…
The task of writer verification is to provide a likelihood score for whether the queried and known handwritten image samples belong to the same writer or not. Such a task calls for the neural network to make it's outcome interpretable, i.e.…
AI-generated text is proliferating across domains, from creative writing and journalism to marketing content and scientific articles. Models can follow user-provided instructions to generate coherent and grammatically correct outputs but in…
Interleaving is an online evaluation approach for information retrieval systems that compares the effectiveness of ranking functions in interpreting the users' implicit feedback. Previous work such as Hofmann et al (2011) has evaluated the…
The effectiveness of Neural Machine Translation (NMT) models largely depends on the vocabulary used at training; small vocabularies can lead to out-of-vocabulary problems -- large ones, to memory issues. Subword (SW) tokenization has been…
Recent advancements in large language models (LLMs) have remarkably enhanced performances on a variety of tasks in multiple languages. However, tokenizers in LLMs trained primarily on English-centric corpora often overly fragment a text…
Tokenizers play a crucial role in determining the performance, training efficiency, and the inference cost of Large Language Models (LLMs). Designing effective tokenizers for multilingual LLMs is particularly challenging due to diverse…
Machine Unlearning (MU) aims to remove the influence of specific data from a trained model while preserving its performance on the remaining data. Although a few works suggest connections between memorisation and augmentation, the role of…
The performance of a machine learning model degrades when it is applied to data from a similar but different domain than the data it has initially been trained on. The goal of domain adaptation (DA) is to mitigate this domain shift problem…
Data augmentation is a ubiquitous technique for improving image classification when labeled data is scarce. Constraining the model predictions to be invariant to diverse data augmentations effectively injects the desired representational…
Vision-Language-Action (VLA) models excel in robotic manipulation but suffer from significant inference latency due to processing dense visual tokens. Existing token reduction methods predominantly rely on attention magnitude as a static…
In active learning, the focus is mainly on the selection strategy of unlabeled data for enhancing the generalization capability of the next learning cycle. For this, various uncertainty measurement methods have been proposed. On the other…