ReGround3D improves understanding of human instructions in 3D environments.
― 4 min read
Xihui Liu
GenArtist enhances image generation and editing with an intelligent AI agent.
― 5 min read
A new benchmark addresses the need for standard evaluation in spatio-temporal prediction.
― 7 min read
OVExp combines language and vision for effective object navigation in varied environments.
― 5 min read
LLaVA-3D combines 2D and 3D insights for deeper spatial reasoning.
― 6 min read
SAMPart3D simplifies 3D model analysis and editing with innovative segmentation techniques.
― 5 min read
New method transforms flat images into vibrant 3D scenes.
― 7 min read
Moto uses video analysis to teach robots complex movements efficiently.
― 5 min read
Discover how V2PE improves Vision-Language Models for better long-context understanding.
― 5 min read
Discover how parallelized generation transforms image and video production.
― 5 min read