4 accepted papers
In this work we present the BDIA-transformer, which is an exact bit-level reversible transformer that uses an unchanged standard architecture for inference. The basic idea is to first treat each transformer block as the Euler integration approximation for solving an ordinary differential equation (O…
"Recently, various methods have been proposed to address the inconsistency issue of DDIM inversion to enable image editing, such as EDICT [?] and Null-text inversion [?]. However, the above methods introduce considerable computational overhead. In this paper, we propose a new technique, named bidire…
"Recent self-supervised approaches have used large-scale image-text datasets to learn powerful representations that transfer to many tasks without finetuning. These methods often assume that there is one-to-one correspondence between its images and their (short) captions. However, many tasks require…
Efficient representation of articulated objects such as human bodies is an important problem in computer vision and graphics. To efficiently simulate deformation, existing approaches represent 3D objects using polygonal meshes and deform them using skinning techniques. This paper introduces neural a…