Search Results for author:
Found 14 papers, 7 papers with code
Normalizing flows for lattice gauge theory in arbitrary space-time dimension
Applications of normalizing flows to the sampling of field configurations in lattice gauge theory have so far been explored almost exclusively in two space-time dimensions.
Aspects of scaling and scalability for flow-based sampling of lattice QCD
Recent applications of machine-learned normalizing flows to sampling in lattice field theory suggest that such methods may be able to mitigate critical slowing down and topological freezing.
A Generalist Agent
Inspired by progress in large-scale language modeling, we apply a similar approach towards building a single generalist agent beyond the realm of text outputs.
Ranked #1 on
Skill Generalization
on RGB-Stacking
Vector Quantized Models for Planning
Our key insight is to use discrete autoencoders to capture the multiple possible effects of an action in a stochastic environment.
Predicting Video with VQVAE
In recent years, the task of video prediction-forecasting future video given past video frames-has attracted attention in the research community.
Ranked #12 on
Video Prediction
on Kinetics-600 12 frames, 64x64
Do Transformers Need Deep Long-Range Memory
Deep attention models have advanced the modelling of sequential data across many domains.
Do Transformers Need Deep Long-Range Memory?
Deep attention models have advanced the modelling of sequential data across many domains.
Data-Efficient Image Recognition with Contrastive Predictive Coding
Human observers can learn to recognize new categories of images from a handful of examples, yet doing so with artificial ones remains an open challenge.
Ranked #6 on
Contrastive Learning
on imagenet-1k
Preventing Posterior Collapse with delta-VAEs
Due to the phenomenon of "posterior collapse," current latent variable generative models pose a challenging design choice that either weakens the capacity of the decoder or requires augmenting the objective so it does not only maximize the likelihood of the data.
Ranked #10 on
Image Generation
on ImageNet 32x32
(bpd metric)
Hyperbolic Attention Networks
We introduce hyperbolic attention networks to endow neural networks with enough capacity to match the complexity of data with hierarchical and power-law structure.
Population Based Training of Neural Networks
Neural networks dominate the modern machine learning landscape, but their training and success still suffer from sensitivity to empirical choices of hyperparameters such as model architecture, loss function, and optimisation algorithm.
