Related papers: Training with Explanations Alone: A New Paradigm t…

The unprecedented performance of machine learning models in recent years, particularly Deep Learning and transformer models, has resulted in their application in various domains such as finance, healthcare, and education. However, the…

Semi-supervised entity alignment (EA) is a practical and challenging task because of the lack of adequate labeled mappings as training data. Most works address this problem by generating pseudo mappings for unlabeled entities. However, they…

Fairness in machine learning seeks to mitigate model bias against individuals based on sensitive features such as sex or age, often caused by an uneven representation of the population in the training data due to selection bias. Notably,…

The application of deep learning in medical imaging has significantly advanced diagnostic capabilities, enhancing both accuracy and efficiency. Despite these benefits, the lack of transparency in these AI models, often termed "black boxes,"…

Despite the remarkable success of text-to-image diffusion models, their output of a single, flattened image remains a critical bottleneck for professional applications requiring layer-wise control. Existing solutions either rely on…

Artificial Intelligence (AI) has the potential to revolutionize diagnosis and segmentation in medical imaging. However, development and clinical implementation face multiple challenges including limited data availability, lack of…

Real-world visual data rarely presents as isolated, static instances. Instead, it often evolves gradually over time through variations in pose, lighting, object state, or scene context. However, conventional classifiers are typically…

Mitigating biases in generative AI and, particularly in text-to-image models, is of high importance given their growing implications in society. The biased datasets used for training pose challenges in ensuring the responsible development…

EXplainable AI (XAI) methods have been proposed to interpret how a deep neural network predicts inputs through model saliency explanations that highlight the parts of the inputs deemed important to arrive a decision at a specific target.…

Masked image modeling (MIM) has become a leading self-supervised learning strategy. MIMs such as Masked Autoencoder (MAE) learn strong representations by randomly masking input tokens for the encoder to process, with the decoder…

Medical imaging machine learning algorithms are usually evaluated on a single dataset. Although training and testing are performed on different subsets of the dataset, models built on one study show limited capability to generalize to other…

The adoption of machine learning in high-stakes applications such as healthcare and law has lagged in part because predictions are not accompanied by explanations comprehensible to the domain user, who often holds the ultimate…

Recent work has raised concerns about the inherent limitations of text-only pretraining. In this paper, we first demonstrate that reporting bias, the tendency of people to not state the obvious, is one of the causes of this limitation, and…

Assessment literacy (AL) is essential for personalized education, yet difficult to cultivate in pre-service teachers. Conventional teacher preparation programs focus on theoretical knowledge, while digital assessment tools commonly provide…

With video-level labels, weakly supervised temporal action localization (WTAL) applies a localization-by-classification paradigm to detect and classify the action in untrimmed videos. Due to the characteristic of classification,…

For doctors to truly trust artificial intelligence, it can't be a black box. They need to understand its reasoning, almost as if they were consulting a colleague. We created HistoLens1 to be that transparent, collaborative partner. It…

AI-enhanced personality assessments are increasingly shaping hiring decisions, using affective computing to predict traits from the Big Five (OCEAN) model. However, integrating AI into these assessments raises ethical concerns, especially…

A feature learning task involves training models that are capable of inferring good representations (transformations of the original space) from input data alone. When working with limited or unlabelled data, and also when multiple visual…

Intelligent systems possess a crucial characteristic of breaking complicated problems into smaller reusable components or parts and adjusting to new tasks using these part representations. However, current part-learners encounter…

In a world increasingly reliant on artificial intelligence, it is more important than ever to consider the ethical implications of artificial intelligence on humanity. One key under-explored challenge is labeler bias, which can create…