Latest AI and machine learning research in surveys for healthcare professionals.
This paper examines how large language models (LLMs) are transforming core quantitative methods in...
Concept-based Models are a class of inherently explainable networks that improve upon standard Dee...
We investigate the existence and persistence of a specific type of gender bias in some of the popu...
Recent advances in Multimodal Large Language Models (MLLMs) have shown promising results in integr...
Person re-identification (ReID) models are known to suffer from camera bias, where learned represe...
Reliability and generalization in deep learning are predominantly studied in the context of image ...
The Internet of Things (IoT) and Large Language Models (LLMs) have been two major emerging players...
Despite the impressive performance of generative Diffusion Models (DMs), their internal working is...
The biases exhibited by text-to-image (TTI) models are often treated as independent, though in rea...
In this work, we propose Dimple, the first Discrete Diffusion Multimodal Large Language Model (DML...
Segment Anything Models (SAM) have achieved remarkable success in object segmentation tasks across...
Medical Visual Question Answering (MedVQA) is crucial for enhancing the efficiency of clinical dia...
Bias in Large Language Models (LLMs) significantly undermines their reliability and fairness. We f...
Vision-Language Models (VLMs) have demonstrated impressive capabilities in understanding visual co...
Personalizing 3D scenes from a single reference image enables intuitive user-guided editing, which...
Popularity bias occurs when popular items are recommended far more frequently than they should be,...
Multilingual vision-language models promise universal image-text retrieval, yet their social biase...
Supervised pretrained models have become widely used in deep learning, especially for image segmen...
Deep learning models often achieve high performance by inadvertently learning spurious correlation...
In Human-Robot Interaction, speech is one of the most intuitive and effective communication channel....
We introduce $\textit{Backward Conformal Prediction}$, a method that guarantees conformal coverage...