ODE$_t$(ODE$_l$): Shortcutting the Time and the Length in Diffusion and Flow Models for Faster Sampling
机构 * Panasonic AI Lab(松下人工智能实验室) ; UC Berkeley(加州大学伯克利分校) ; Panasonic DX-CPS(松下DX-CPS)
Comments Accepted to WACV 2026. Preprint. Github page: github.com/gudovskiy/odelt