Related papers: Refinement of genetic variants needs attention

DNA language models are increasingly used to represent genomic sequence, yet their effectiveness depends critically on how raw nucleotides are converted into model inputs. Unlike natural language, DNA offers no canonical boundaries, making…

Underwater images often exhibit poor quality, distorted color balance and low contrast due to the complex and intricate interplay of light, water, and objects. Despite the significant contributions of previous underwater enhancement…

The task of understanding and interpreting the complex information encoded within genomic sequences remains a grand challenge in biological research and clinical applications. In this context, recent advancements in large language model…

We present a deep transformation model for probabilistic regression. Deep learning is known for outstandingly accurate predictions on complex data but in regression tasks, it is predominantly used to just predict a single number. This…

Weakly-supervised anomaly detection aims at learning an anomaly detector from a limited amount of labeled data and abundant unlabeled data. Recent works build deep neural networks for anomaly detection by discriminatively mapping the normal…

Deep learning models often rely only on a small set of features even when there is a rich set of predictive signals in the training data. This makes models brittle and sensitive to distribution shifts. In this work, we first examine vision…

It is increasingly common clinically for cancer specimens to be examined using techniques that identify somatic mutations. In principle these mutational profiles can be used to diagnose the tissue of origin, a critical task for the 3-5% of…

Transformers evaluated in a single, fixed-depth pass are provably limited in expressive power to the constant-depth circuit class TC0. Running a Transformer autoregressively removes that ceiling -- first in next-token prediction and, more…

Transformer-based models have emerged as promising tools for time series forecasting. However, these model cannot make accurate prediction for long input time series. On the one hand, they failed to capture global dependencies within time…

This paper proves a new watermarking method to embed the ownership information into a deep neural network (DNN), which is robust to fine-tuning. Specifically, we prove that when the input feature of a convolutional layer only contains…

High-quality speech corpora are essential foundations for most speech applications. However, such speech data are expensive and limited since they are collected in professional recording environments. In this work, we propose an…

Utilizing complex-valued neural networks (CVNNs) in wireless communication tasks has received growing attention for their ability to provide natural and effective representation of complex-valued signals and data. However, existing studies…

Identifiers, such as method and variable names, form a large portion of source code. Therefore, low-quality identifiers can substantially hinder code comprehension. To support developers in using meaningful identifiers, several…

Transformers are very powerful tools for a variety of tasks across domains, from text generation to image captioning. However, transformers require substantial amounts of training data, which is often a challenge in biomedical settings,…

Fine-tuned transformer models have shown superior performances in many natural language tasks. However, the large model size prohibits deploying high-performance transformer models on resource-constrained devices. This paper proposes a…

Referring image segmentation aims to segment an object referred to by natural language expression from an image. The primary challenge lies in the efficient propagation of fine-grained semantic information from textual features to visual…

Breast cancer is a major global health issue that affects millions of women worldwide. Classification of breast cancer as early and accurately as possible is crucial for effective treatment and enhanced patient outcomes. Deep transfer…

We present a holistic approach for high resolution image classification that won second place in the ICCV/CVPPA2023 Deep Nutrient Deficiency Challenge. The approach consists of a full pipeline of: 1) data distribution analysis to check…

Protecting patient privacy in healthcare records is a top priority, and redaction is a commonly used method for obscuring directly identifiable information in text. Rule-based methods have been widely used, but their precision is often low…

Transformer is a ubiquitous model for natural language processing and has attracted wide attentions in computer vision. The attention maps are indispensable for a transformer model to encode the dependencies among input tokens. However,…