VcEdit improves 3D editing by ensuring consistency across multiple views.
― 5 min read
Hanwang Zhang
DTC123 improves 3D model generation from single images using teaching models.
― 6 min read
A new method reduces time and cost in training diffusion models.
― 7 min read
Setokim enhances the fusion of visual and text understanding through innovative tokenization.
― 8 min read
New method optimizes image segmentation by diversifying context examples.
― 5 min read
A new strategy combines generative and discriminative training in Vision-Language Models.
― 5 min read
A new method enhances model performance on diverse data types.
― 5 min read