Latest AI and machine learning research in cultural competence for healthcare professionals.
Training-free video large language models (LLMs) leverage pretrained Image LLMs to process video content without the need for further training. A key challenge in such approaches is the difficulty of retaining essential visual and temporal information, constrained by the token limits in Image LLMs. To address this, we propose a two-stage method for selecting query-relevant tokens based on the LL...
Recommendation systems have found extensive applications across diverse domains. However, the training data available typically comprises implicit feedback, manifested as user clicks and purchase behaviors, rather than explicit declarations of user preferences. This type of training data presents three main challenges for accurate ranking prediction: First, the unobservable nature of user prefer...
Writing Assistants (e.g., Grammarly, Microsoft Copilot) traditionally generate diverse image captions by employing syntactic and semantic variations...
Retrieval-Augmented Generation (RAG) enables large language models to provide more precise and pertinent responses by incorporating external knowled...
Neural architectures tend to fit their data with relatively simple functions. This "simplicity bias" is widely regarded as key to their success. Thi...
Data-driven AI is establishing itself at the center of evidence-based medicine. However, reports of shortcomings and unexpected behavior are growing...
Text-to-image person re-identification (ReID) aims to retrieve the images of an interested person based on textual descriptions. One main challenge ...
The biases exhibited by Text-to-Image (TTI) models are often treated as if they are independent, but in reality, they may be deeply interrelated. Ad...
Foodborne gastrointestinal (GI) illness is a common cause of ill health in the UK. However, many cases do not interact with the healthcare system, p...
Transformers, particularly Vision Transformers (ViTs), have achieved state-of-the-art performance in large-scale image classification. However, they...
To improve trust and transparency, it is crucial to be able to interpret the decisions of Deep Neural classifiers (DNNs). Instance-level examination...
In the domain of emotion recognition using body motion, the primary challenge lies in the scarcity of diverse and generalizable datasets. Automatic ...
The application of machine learning (ML) to electroencephalography (EEG) has great potential to advance both neuroscientific research and clinical a...
The success of multi-modal large language models (MLLMs) has been largely attributed to the large-scale training data. However, the training data of...
Previous studies have found that PLM-based retrieval models exhibit a preference for LLM-generated content, assigning higher relevance scores to the...
The increasing prevalence of synthetic data in training loops has raised concerns about model collapse, where generative models degrade when trained...
We investigate bias trends in text-to-image generative models over time, focusing on the increasing availability of models through open platforms li...
Southeast Asia (SEA) is a region of extraordinary linguistic and cultural diversity, yet it remains significantly underrepresented in vision-languag...
When we train models on biased ML datasets, they not only learn these biases but can inflate them at test time - a phenomenon called bias amplificat...
Rapid advancement of diffusion models has catalyzed remarkable progress in the field of image generation. However, prevalent models such as Flux, SD...