LISA improves machine understanding of complex user instructions.
― 6 min read
Yuhui Yuan
This paper examines pre-training methods to improve DETR model performance in object detection.
― 5 min read
Improving object detection efficiency while maintaining simplicity.
― 5 min read
A new method enhances 3D instance segmentation by removing mask attention reliance.
― 5 min read
CCEdit simplifies video editing by separating structure and appearance control.
― 5 min read
A new text encoder tackles challenges in visual text rendering.
― 4 min read
A new model generates unique font effects for multiple languages.
― 5 min read
New methods enhance text rendering quality in multiple languages.
― 5 min read
A new framework enhances image generation speed and quality in diffusion transformers.
― 5 min read