Abstract: Multi-aspect controllable text generation (CTG), opposite to single-aspect CTG, aims to produce texts that align with multiple attributes. Incorporating attribute information through ...
AI-generated images are getting increasingly realistic, yet there are still telltale details that can reveal when something is fake. I’ve been writing about consumer technology and video games for ...
Abstract: Current text-to-avatar methods often rely on implicit representations (e.g., NeRF, SDF, and DMTet), leading to 3D content that artists cannot easily edit and animate in graphics software.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results