Fine-grained, continuous control over multiple attributes at once (e.g., exact eye-openness and car width) on top of any pretrained diffusion model. A decoupled cross-attention layer that cleanly ...

Abstract: One of the most crucial abilities for robots is to grasp objects accurately in cluttered scenes. This article proposes a structured local feature-conditioned 6-DOF variational grasp ...

Abstract: Vector quantized variational autoencoders, as variants of variational autoencoders, effectively capture discrete representations by quantizing continuous latent spaces and are widely used in ...