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...
Nesta página do site você pode assistir ao vídeo on-line Spline-based Transformers duração hora minuto segundo em boa qualidade , que foi baixado pelo usuário DisneyResearchHub 23 Setembro 2024, compartilhe o link com seus amigos e conhecidos, no youtube este vídeo já foi visto 5,506 vezes e gostou like espectadores. Boa visualização!
