Related papers: Improving Applicability of Deep Learning based Tok…

Reproducibility is an increasing concern in Artificial Intelligence (AI), particularly in the area of Deep Learning (DL). Being able to reproduce DL models is crucial for AI-based systems, as it is closely tied to various tasks like…

Diffusion language models (DLMs) have shown strong potential for general natural language tasks with in-context examples. However, due to the bidirectional attention mechanism, DLMs incur substantial computational cost as context length…

Despite the recent success of image-text contrastive models like CLIP and SigLIP, these models often struggle with vision-centric tasks that demand high-fidelity image understanding, such as counting, depth estimation, and fine-grained…

Classical sequential recommendation models generally adopt ID embeddings to store knowledge learned from user historical behaviors and represent items. However, these unique IDs are challenging to be transferred to new domains. With the…

Distance metric learning (DML) approaches learn a transformation to a representation space where distance is in correspondence with a predefined notion of similarity. While such models offer a number of compelling benefits, it has been…

While traditional Deep Learning (DL) optimization methods treat all training samples equally, Distributionally Robust Optimization (DRO) adaptively assigns importance weights to different samples. However, a significant gap exists between…

Instruction tuning plays a critical role in enhancing the performance and efficiency of Large Language Models (LLMs). Its success depends not only on the quality of the instruction data but also on the inherent capabilities of the LLM…

Purpose: This study evaluates the effectiveness and impact of automated order-based protocol assignment for magnetic resonance imaging (MRI) exams using natural language processing (NLP) and deep learning (DL). Methods: NLP tools were…

State-of-the-art deep neural network recognition systems are designed for a static and closed world. It is usually assumed that the distribution at test time will be the same as the distribution during training. As a result, classifiers are…

Privacy-preserving machine learning aims to train models on private data without leaking sensitive information. Differential privacy (DP) is considered the gold standard framework for privacy-preserving training, as it provides formal…

In recent years, with the rapid development of information on the Internet, the number of complex texts and documents has increased exponentially, which requires a deeper understanding of deep learning methods in order to accurately…

Domain-Adaptive Pre-training (DAP) has recently gained attention for its effectiveness in fine-tuning pre-trained models. Building on this, continual DAP has been explored to develop pre-trained models capable of incrementally incorporating…

Data-efficient image classification using deep neural networks in settings, where only small amounts of labeled data are available, has been an active research area in the recent past. However, an objective comparison between published…

Training data influence estimation methods quantify the contribution of training documents to a model's output, making them a promising source of information for example-based explanations. As humans cannot interpret thousands of documents,…

Deep neural networks can be unreliable in the real world when the training set does not adequately cover all the settings where they are deployed. Focusing on image classification, we consider the setting where we have an error distribution…

Data augmentation by mixing samples, such as Mixup, has widely been used typically for classification tasks. However, this strategy is not always effective due to the gap between augmented samples for training and original samples for…

Representation learning is a critical ingredient for natural language processing systems. Recent Transformer language models like BERT learn powerful textual representations, but these models are targeted towards token- and sentence-level…

Decision tree ensembles are widely used in critical domains, making robustness and sensitivity analysis essential to their trustworthiness. We study the feature sensitivity problem, which asks whether an ensemble is sensitive to a specified…

Deep neural networks have achieved significant improvements in information retrieval (IR). However, most existing models are computational costly and can not efficiently scale to long documents. This paper proposes a novel End-to-End neural…

Data attribution methods are used to measure the contribution of training data towards model outputs, and have several important applications in areas such as dataset curation and model interpretability. However, many standard data…