Search Results for author:
Found 50 papers, 29 papers with code
Simpler Diffusion (SiD2): 1.5 FID on ImageNet512 with pixel-space diffusion
Compared to pixel-space models that are trained end-to-end, latent models are perceived to be more efficient and to produce higher image quality at high resolution.
Ranked #1 on
Image Generation
on ImageNet 128x128
Multistep Distillation of Diffusion Models via Moment Matching
We present a new method for making diffusion models faster to sample.
EM Distillation for One-step Diffusion Models
We propose EM Distillation (EMD), a maximum likelihood-based approach that distills a diffusion model to a one-step generator model with minimal loss of perceptual quality.
Multistep Consistency Models
By increasing the sample budget from a single step to 2-8 steps, we can train models more easily that generate higher quality samples, while retaining much of the sampling speed benefits.
Rolling Diffusion Models
Diffusion models have recently been increasingly applied to temporal data such as video, fluid mechanics simulations, or climate data.
Simple diffusion: End-to-end diffusion for high resolution images
Currently, applying diffusion models in pixel space of high resolution images is difficult.
Ranked #4 on
Conditional Image Generation
on ImageNet 128x128
On Distillation of Guided Diffusion Models
For standard diffusion models trained on the pixel-space, our approach is able to generate images visually comparable to that of the original model using as few as 4 sampling steps on ImageNet 64x64 and CIFAR-10, achieving FID/IS scores comparable to that of the original model while being up to 256 times faster to sample from.
Imagen Video: High Definition Video Generation with Diffusion Models
We present Imagen Video, a text-conditional video generation system based on a cascade of video diffusion models.
Ranked #1 on
Video Generation
on LAION-400M
Blurring Diffusion Models
Recently, Rissanen et al., (2022) have presented a new type of diffusion process for generative modeling based on heat dissipation, or blurring, as an alternative to isotropic Gaussian diffusion.
Classifier-Free Diffusion Guidance
Classifier guidance is a recently introduced method to trade off mode coverage and sample fidelity in conditional diffusion models post training, in the same spirit as low temperature sampling or truncation in other types of generative models.
Lossy Compression with Gaussian Diffusion
Unlike modern compression schemes which rely on transform coding and quantization to restrict the transmitted information, DiffC relies on the efficient communication of pixels corrupted by Gaussian noise.
Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding
We present Imagen, a text-to-image diffusion model with an unprecedented degree of photorealism and a deep level of language understanding.
Ranked #16 on
Text-to-Image Generation
on MS COCO
(using extra training data)
Video Diffusion Models
Generating temporally coherent high fidelity video is an important milestone in generative modeling research.
Progressive Distillation for Fast Sampling of Diffusion Models
Second, we present a method to distill a trained deterministic diffusion sampler, using many steps, into a new diffusion model that takes half as many sampling steps.
Ranked #45 on
Image Generation
on CIFAR-10
On Density Estimation with Diffusion Models
In addition, we show that the continuous-time VLB is invariant to the noise schedule, except for the signal-to-noise ratio at its endpoints.
Palette: Image-to-Image Diffusion Models
We expect this standardized evaluation protocol to play a role in advancing image-to-image translation research.
Ranked #1 on
Colorization
on ImageNet ctest10k
Autoregressive Diffusion Models
We introduce Autoregressive Diffusion Models (ARDMs), a model class encompassing and generalizing order-agnostic autoregressive models (Uria et al., 2014) and absorbing discrete diffusion (Austin et al., 2021), which we show are special cases of ARDMs under mild assumptions.
Ranked #10 on
Image Generation
on CIFAR-10
(bits/dimension metric)
Unconditional Diffusion Guidance
Classifier guidance is a recently introduced method to trade off mode coverage and sample fidelity in conditional diffusion models post training, in the same spirit as low temperature sampling or truncation in other types of generative models.
Variational Diffusion Models
In addition, we show that the continuous-time VLB is invariant to the noise schedule, except for the signal-to-noise ratio at its endpoints.
Ranked #2 on
Density Estimation
on CIFAR-10
Cascaded Diffusion Models for High Fidelity Image Generation
We show that cascaded diffusion models are capable of generating high fidelity images on the class-conditional ImageNet generation benchmark, without any assistance from auxiliary image classifiers to boost sample quality.
Ranked #8 on
Image Generation
on ImageNet 64x64
Agent-Centric Representations for Multi-Agent Reinforcement Learning
Empirically, agent-centric representation learning leads to the emergence of more complex cooperation strategies between agents as well as enhanced sample efficiency and generalization.
Image Super-Resolution via Iterative Refinement
We present SR3, an approach to image Super-Resolution via Repeated Refinement.
Should EBMs model the energy or the score?
Recent progress in training unnormalized models through denoising score matching with Langevin dynamics (SMLD) and denoising diffusion probabilistic modeling (DDPM) has made unnormalized models a competitive model class for generative modeling.
A Spectral Energy Distance for Parallel Speech Synthesis
Speech synthesis is an important practical generative modeling problem that has seen great progress over the last few years, with likelihood-based autoregressive neural models now outperforming traditional concatenative systems.
IDF++: Analyzing and Improving Integer Discrete Flows for Lossless Compression
Furthermore, we zoom in on the effect of gradient bias due to the straight-through estimator in integer discrete flows, and demonstrate that its influence is highly dependent on architecture choices and less prominent than previously thought.
Milking CowMask for Semi-Supervised Image Classification
Using it to provide perturbations for semi-supervised consistency regularization, we achieve a state-of-the-art result on ImageNet with 10% labeled data, with a top-5 error of 8. 76% and top-1 error of 26. 06%.
MetNet: A Neural Weather Model for Precipitation Forecasting
Weather forecasting is a long standing scientific challenge with direct social and economic impact.
The k-tied Normal Distribution: A Compact Parameterization of Gaussian Mean Field Posteriors in Bayesian Neural Networks
Variational Bayesian Inference is a popular methodology for approximating posterior distributions over Bayesian neural network weights.
How Good is the Bayes Posterior in Deep Neural Networks Really?
In this work we cast doubt on the current understanding of Bayes posteriors in popular deep neural networks: we demonstrate through careful MCMC sampling that the posterior predictive induced by the Bayes posterior yields systematically worse predictions compared to simpler methods including point estimates obtained from SGD.
Hydra: Preserving Ensemble Diversity for Model Distillation
As a result, the diversity of the ensemble predictions, stemming from each member, is lost.
Axial Attention in Multidimensional Transformers
We propose Axial Transformers, a self-attention-based autoregressive model for images and other data organized as high dimensional tensors.
Ranked #29 on
Image Generation
on ImageNet 64x64
(Bits per dim metric)
Dota 2 with Large Scale Deep Reinforcement Learning
On April 13th, 2019, OpenAI Five became the first AI system to defeat the world champions at an esports game.
On the Parameterization of Gaussian Mean Field Posteriors in Bayesian Neural Networks
Variational Bayesian Inference is a popular methodology for approximating posterior distributions in Bayesian neural networks.
The Likelihood of Mixed Hitting Times
We present a method for computing the likelihood of a mixed hitting-time model that specifies durations as the first time a latent L\'evy process crosses a heterogeneous threshold.
Policy Gradient Search: Online Planning and Expert Iteration without Search Trees
Monte Carlo Tree Search (MCTS) algorithms perform simulation-based search to improve policies online.
On the relationship between Normalising Flows and Variational- and Denoising Autoencoders
Normalising Flows (NFs) are a class of likelihood-based generative models that have recently gained popularity.
Learning Montezuma's Revenge from a Single Demonstration
We propose a new method for learning from a single demonstration to solve hard exploration tasks like the Atari game Montezuma's Revenge.
Improving Language Understanding by Generative Pre-Training
We demonstrate that large gains on these tasks can be realized by generative pre-training of a language model on a diverse corpus of unlabeled text, followed by discriminative fine-tuning on each specific task.
Ranked #3 on
Natural Language Inference
on SciTail
Improving GANs Using Optimal Transport
We present Optimal Transport GAN (OT-GAN), a variant of generative adversarial nets minimizing a new metric measuring the distance between the generator distribution and the data distribution.
Evolution Strategies as a Scalable Alternative to Reinforcement Learning
We explore the use of Evolution Strategies (ES), a class of black box optimization algorithms, as an alternative to popular MDP-based RL techniques such as Q-learning and Policy Gradients.
Ranked #1 on
Atari Games
on Atari 2600 Pong
PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modifications
1) We use a discretized logistic mixture likelihood on the pixels, rather than a 256-way softmax, which we find to speed up training.
Ranked #4 on
Density Estimation
on CIFAR-10
Improved Variational Inference with Inverse Autoregressive Flow
The framework of normalizing flows provides a general strategy for flexible variational inference of posteriors over latent variables.
Ranked #44 on
Image Generation
on CIFAR-10
(bits/dimension metric)
Variational Lossy Autoencoder
Representation learning seeks to expose certain aspects of observed data in a learned representation that's amenable to downstream tasks like classification.
Improving Variational Inference with Inverse Autoregressive Flow
The framework of normalizing flows provides a general strategy for flexible variational inference of posteriors over latent variables.
Improved Techniques for Training GANs
We present a variety of new architectural features and training procedures that we apply to the generative adversarial networks (GANs) framework.
Ranked #15 on
Conditional Image Generation
on CIFAR-10
(Inception score metric)
Conditional Image Generation
Semi-Supervised Image Classification
A Structured Variational Auto-encoder for Learning Deep Hierarchies of Sparse Features
To learn the parameters of the new model, we approximate the posterior of the latent variables with a variational auto-encoder.
Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks
We present weight normalization: a reparameterization of the weight vectors in a neural network that decouples the length of those weight vectors from their direction.
Variational Dropout and the Local Reparameterization Trick
Our method allows inference of more flexibly parameterized posteriors; specifically, we propose variational dropout, a generalization of Gaussian dropout where the dropout rates are learned, often leading to better models.
Markov Chain Monte Carlo and Variational Inference: Bridging the Gap
Recent advances in stochastic gradient variational inference have made it possible to perform variational Bayesian inference with posterior approximations containing auxiliary random variables.
Fixed-Form Variational Posterior Approximation through Stochastic Linear Regression
We propose a general algorithm for approximating nonstandard Bayesian posterior distributions.
