Search Results for author:
Found 8 papers, 3 papers with code
SMiRL: Surprise Minimizing RL in Entropic Environments
All living organisms struggle against the forces of nature to carve out niches where they can maintain relative stasis.
Unsupervised Pre-training
Unsupervised Reinforcement Learning
Plan Arithmetic: Compositional Plan Vectors for Multi-Task Control
We show that CPVs can be learned within a one-shot imitation learning framework without any additional supervision or information about task hierarchy, and enable a demonstration-conditioned policy to generalize to tasks that sequence twice as many skills as the tasks seen during training.
Compositional Plan Vectors
We show that CPVs can be learned within a one-shot imitation learning framework without any additional supervision or information about task hierarchy, and enable a demonstration-conditioned policy to generalize to tasks that sequence twice as many skills as the tasks seen during training.
SMiRL: Surprise Minimizing Reinforcement Learning in Unstable Environments
Every living organism struggles against disruptive environmental forces to carve out and maintain an orderly niche.
Comparing Correspondences: Video Prediction with Correspondence-wise Losses
Image prediction methods often struggle on tasks that require changing the positions of objects, such as video prediction, producing blurry images that average over the many positions that objects might occupy.
Visual Anagrams: Generating Multi-View Optical Illusions with Diffusion Models
During the reverse diffusion process, we estimate the noise from different views of a noisy image, and then combine these noise estimates together and denoise the image.
Motion Guidance: Diffusion-Based Image Editing with Differentiable Motion Estimators
Diffusion models are capable of generating impressive images conditioned on text descriptions, and extensions of these models allow users to edit images at a relatively coarse scale.
Factorized Diffusion: Perceptual Illusions by Noise Decomposition
And we explore a decomposition by a motion blur kernel, which produces images that change appearance under motion blurring.
