New research reveals that despite possessing vast knowledge, AI storytellers often perpetuate cultural misrepresentations, particularly when venturing beyond Western narratives.
Researchers have developed a novel framework that focuses on tracking specific regions of interest within videos to achieve more accurate fine-grained action recognition.
A new deep learning approach leverages convolutional neural networks to accurately determine the geometry and material properties of obscured objects from electromagnetic scattering data.
A new framework, Contrastive Fusion, leverages both pairwise and higher-order relationships to significantly enhance multimodal representation learning.
A new approach to remote sensing foundation models demonstrates that an ensemble of focused AI experts can achieve competitive performance with dramatically reduced computational demands.
A new framework dynamically adjusts prompt tokens to unlock better performance and generalization in vision-language models.
Researchers are demonstrating that techniques originally developed for image inpainting can be powerfully repurposed for the complex task of decomposing images into their constituent layers.
A new approach, ToolOrchestra, efficiently coordinates diverse AI models and tools to achieve peak performance with reduced costs and improved alignment with user needs.
A new study demonstrates that directly comparing outputs from text-to-image models fundamentally changes how users evaluate and understand their underlying behaviors.
New research explores whether refining large language models with small amounts of human behavioral data can improve their ability to simulate human reasoning and decision-making.