Related papers: Central Dogma Transformer: Towards Mechanism-Orien…

Capturing images with incorrect exposure settings fails to deliver a satisfactory visual experience. Only when the exposure is properly set, can the color and details of the images be appropriately preserved. Previous exposure correction…

Deep neural networks need to make robust inference in the presence of occlusion, background clutter, pose and viewpoint variations -- to name a few -- when the task of person re-identification is considered. Attention mechanisms have…

From customer feedback to social media, understanding human sentiment in text is central to how machines can interact meaningfully with people. However, despite notable progress, accurately capturing sentiment remains a challenging task,…

Text understanding often suffers from domain shifts. To handle testing domains, domain adaptation (DA) is trained to adapt to a fixed and observed testing domain; a more challenging paradigm, test-time adaptation (TTA), cannot access the…

Since context modeling is critical for estimating depth from a single image, researchers put tremendous effort into obtaining global context. Many global manipulations are designed for traditional CNN-based architectures to overcome the…

Data-centric distillation, including data augmentation, selection, and mixing, offers a promising path to creating smaller, more efficient student Large Language Models (LLMs) that retain strong reasoning abilities. However, there still…

Deep convolutional neural networks (CNNs) have been applied to extracting speaker embeddings with significant success in speaker verification. Incorporating the attention mechanism has shown to be effective in improving the model…

This paper investigates the application of the transformer architecture in protein folding, as exemplified by DeepMind's AlphaFold project, and its implications for the understanding of so-called large language models. The prevailing…

Continual Test-Time Adaptation (CTTA) generalizes conventional Test-Time Adaptation (TTA) by assuming that the target domain is dynamic over time rather than stationary. In this paper, we explore Multi-Modal Continual Test-Time Adaptation…

In recent years, molecular representation learning has emerged as a key area of focus in various chemical tasks. However, many existing models fail to fully consider the geometric information of molecular structures, resulting in less…

Change detection (CD) is one of the most vital applications in remote sensing. Recently, deep learning has achieved promising performance in the CD task. However, the deep models are task-specific and CD data set bias often exists, hence it…

Many multi-domain neural machine translation (NMT) models achieve knowledge transfer by enforcing one encoder to learn shared embedding across domains. However, this design lacks adaptation to individual domains. To overcome this…

Deep learning methods based on Convolutional Neural Networks (CNNs) have shown great potential to improve early and accurate diagnosis of Alzheimer's disease (AD) dementia based on imaging data. However, these methods have yet to be widely…

Transformers have shown superior performance on various vision tasks. Their large receptive field endows Transformer models with higher representation power than their CNN counterparts. Nevertheless, simply enlarging the receptive field…

Time-continuous emotion prediction has become an increasingly compelling task in machine learning. Considerable efforts have been made to advance the performance of these systems. Nonetheless, the main focus has been the development of more…

Automated mechanistic interpretation research has attracted great interest due to its potential to scale explanations of neural network internals to large models. Existing automated circuit discovery work relies on activation patching or…

Deep neural networks often suffer performance degradation upon deployment due to distribution shifts. Continual Test-Time Adaptation (CTTA) aims to address this issue in an unsupervised manner. However, existing methods that rely on…

Multimodal MR-US registration is critical for prostate cancer diagnosis. However, this task remains challenging due to significant modality discrepancies. Existing methods often fail to align critical boundaries while being overly sensitive…

Neural Machine Translation (NMT) models have shown remarkable performance but remain largely opaque in their decision making processes. The interpretability of these models, especially their internal attention mechanisms, is critical for…

The accurate analysis of medical images is vital for diagnosing and predicting medical conditions. Traditional approaches relying on radiologists and clinicians suffer from inconsistencies and missed diagnoses. Computer-aided diagnosis…