Search Results for author:
Found 11 papers, 5 papers with code
Semantically Consistent Video Inpainting with Conditional Diffusion Models
Current state-of-the-art methods for video inpainting typically rely on optical flow or attention-based approaches to inpaint masked regions by propagating visual information across frames.
Visual Chain-of-Thought Diffusion Models
Recent progress with conditional image diffusion models has been stunning, and this holds true whether we are speaking about models conditioned on a text description, a scene layout, or a sketch.
Graphically Structured Diffusion Models
We introduce a framework for automatically defining and learning deep generative models with problem-specific structure.
Flexible Diffusion Modeling of Long Videos
We present a framework for video modeling based on denoising diffusion probabilistic models that produces long-duration video completions in a variety of realistic environments.
Conditional Image Generation by Conditioning Variational Auto-Encoders
We present a conditional variational auto-encoder (VAE) which, to avoid the substantial cost of training from scratch, uses an architecture and training objective capable of leveraging a foundation model in the form of a pretrained unconditional VAE.
Near-Optimal Glimpse Sequences for Training Hard Attention Neural Networks
We introduce methodology from the BOED literature to approximate this optimal behaviour, and use it to generate `near-optimal' sequences of attention locations.
Assisting the Adversary to Improve GAN Training
Some of the most popular methods for improving the stability and performance of GANs involve constraining or regularizing the discriminator.
Planning as Inference in Epidemiological Models
In this work we demonstrate how to automate parts of the infectious disease-control policy-making process via performing inference in existing epidemiological models.
Attention for Inference Compilation
We present a new approach to automatic amortized inference in universal probabilistic programs which improves performance compared to current methods.
Efficient Inference Amortization in Graphical Models using Structured Continuous Conditional Normalizing Flows
We introduce a more efficient neural architecture for amortized inference, which combines continuous and conditional normalizing flows using a principled choice of structure.
Near-Optimal Glimpse Sequences for Improved Hard Attention Neural Network Training
We introduce methodology from the BOED literature to approximate this optimal behaviour, and use it to generate `near-optimal' sequences of attention locations.
