Spline-based Transformers
We introduce Spline-based Transformers, a novel class of Transformer models that eliminate the need for positional encoding. Inspired by workflows using splines in computer animation, our Spline-based Transformers embed an input sequence of elements as a smooth
trajectory in latent space. Overcoming drawbacks of positional encoding
such as sequence length extrapolation, Spline-based Transformers also
provide a novel way for users to interact with transformer latent spaces
by directly manipulating the latent control points to create new latent
trajectories and sequences. We demonstrate the superior performance of
our approach in comparison to conventional positional encoding on a
variety of datasets, ranging from synthetic 2D to large-scale real-world
datasets of images, 3D shapes, and animations.
Publication link: https://la.disneyresearch.com/publica...
On this page of the site you can watch the video online Spline-based Transformers with a duration of hours minute second in good quality, which was uploaded by the user DisneyResearchHub 23 September 2024, share the link with friends and acquaintances, this video has already been watched 5,506 times on youtube and it was liked by like viewers. Enjoy your viewing!
