About
Research & Development
X-UniMotion: A New Era for Expressive Human Image Animation
TLDR: X-UniMotion is a novel AI system that animates still human images using motion from a video, even if the subjects are different. It...
Research & Development
RelayFormer: Scalable Manipulation Localization for Visual Content
TLDR: RelayFormer is a new AI framework designed to accurately detect tampered regions in both images and videos. It overcomes limitations of existing methods...
Research & Development
Unlocking Long Video Understanding: A Human-Inspired Memory Approach for AI
TLDR: Video-EM is a new training-free framework that helps AI models understand long videos better by mimicking human episodic memory. It identifies key events,...
Research & Development
MInDI-3D: Enhancing Medical Scans with Deep Learning for Reduced Radiation
TLDR: MInDI-3D is a new 3D deep learning model that uses an iterative denoising process to remove artifacts from sparse-view Cone Beam Computed Tomography...
Research & Development
Preacher: Automating Research Paper Summaries into Engaging Video Abstracts
TLDR: Preacher is the first agentic system that converts research papers into structured video abstracts. It uses a top-down approach to decompose and summarize...
Research & Development
A New Framework for Understanding Individual Brain Development and Cortical Folding
TLDR: NEUBORN is a novel deep learning framework that uses biomechanical constraints to accurately model individual brain growth trajectories from longitudinal MRI scans. It...