Related papers: Token Imbalance Adaptation for Radiology Report Ge…

From the ad network standpoint, a user's activity is a multi-type sequence of temporal events consisting of event types and time intervals. Understanding user patterns in ad networks has received increasing attention from the machine…

Language models are often trained to maximize the likelihood of the next token given past tokens in the training dataset. However, during inference time, they are utilized differently, generating text sequentially and auto-regressively by…

Token-level adaptive training approaches can alleviate the token imbalance problem and thus improve neural machine translation, through re-weighting the losses of different target tokens based on specific statistical metrics (e.g., token…

Automated Radiology report generation (RRG) aims at producing detailed descriptions of medical images, reducing radiologists' workload and improving access to high-quality diagnostic services. Existing encoder-decoder models only rely on…

There have been tremendous efforts over the past decades dedicated to the generation of realistic graphs in a variety of domains, ranging from social networks to computer networks, from gene regulatory networks to online transaction…

Automated radiology report generation (R2Gen) has advanced significantly, introducing challenges in accurate evaluation due to its complexity. Traditional metrics often fall short by relying on rigid word-matching or focusing only on…

Automated Machine Learning has grown very successful in automating the time-consuming, iterative tasks of machine learning model development. However, current methods struggle when the data is imbalanced. Since many real-world datasets are…

This paper argues that generating output tokens is more effective than using pooled representations for prediction tasks because token-level generation retains more mutual information. Since LLMs are trained on massive text corpora using…

With the ever increasing data deluge and the success of deep neural networks, the research of distributed deep learning has become pronounced. Two common approaches to achieve this distributed learning is synchronous and asynchronous weight…

Image-to-image translation is an ill-posed problem as unique one-to-one mapping may not exist between the source and target images. Learning-based methods proposed in this context often evaluate the performance on test data that is similar…

Radiology report generation (RRG) has shown great potential in assisting radiologists by automating the labor-intensive task of report writing. While recent advancements have improved the quality and coherence of generated reports, ensuring…

Radiology reports are a rich resource for advancing deep learning applications in medicine by leveraging the large volume of data continuously being updated, integrated, and shared. However, there are significant challenges as well, largely…

Traditional language models operate autoregressively, i.e., they predict one token at a time. Rapid explosion in model sizes has resulted in high inference times. In this work, we propose DynaMo, a suite of multi-token prediction language…

While deep learning holds great promise for disease diagnosis and prognosis in cardiac magnetic resonance imaging, its progress is often constrained by highly imbalanced and biased training datasets. To address this issue, we propose a…

Natural Language Generation (NLG) models are prone to generating repetitive utterances. In this work, we study the repetition problem for encoder-decoder models, using both recurrent neural network (RNN) and transformer architectures. To…

With the emergence of large model-based agents, widely adopted transformer-based architectures inevitably produce excessively long token embeddings for transmission, which may result in high bandwidth overhead, increased power consumption…

Text generation tasks, including translation, summarization, language models, and etc. see rapid growth during recent years. Despite the remarkable achievements, the repetition problem has been observed in nearly all text generation models…

Can continuous diffusion models bring the same performance breakthrough on natural language they did for image generation? To circumvent the discrete nature of text data, we can simply project tokens in a continuous space of embeddings, as…

BACKGROUND: Radiology reports are typically written in a free-text format, making clinical information difficult to extract and use. Recently the adoption of structured reporting (SR) has been recommended by various medical societies thanks…

Recent advances in image tokenizers, such as VQ-VAE, have enabled text-to-image generation using auto-regressive methods, similar to language modeling. However, these methods have yet to leverage pre-trained language models, despite their…