research
∙
10/12/2022
Self-supervised video pretraining yields strong image representations
Videos contain far more information than still images and hold the poten...
share
research
∙
01/28/2022
From data to functa: Your data point is a function and you should treat it like one
It is common practice in deep learning to represent a measurement of the...
research
∙
06/26/2021
Inferring a Continuous Distribution of Atom Coordinates from Cryo-EM Images using VAEs
Cryo-electron microscopy (cryo-EM) has revolutionized experimental prote...
research
∙
06/25/2021
Multimodal Few-Shot Learning with Frozen Language Models
When trained at sufficient scale, auto-regressive language models exhibi...
research
∙
05/25/2021
From Motor Control to Team Play in Simulated Humanoid Football
Intelligent behaviour in the physical world exhibits structure at multip...
research
∙
05/01/2021
Generative Art Using Neural Visual Grammars and Dual Encoders
Whilst there are perhaps only a few scientific methods, there seem to be...
research
∙
07/10/2020
Contrastive Training for Improved Out-of-Distribution Detection
Reliable detection of out-of-distribution (OOD) inputs is increasingly u...
research
∙
02/23/2020
PolyGen: An Autoregressive Generative Model of 3D Meshes
Polygon meshes are an efficient representation of 3D geometry, and are o...
research
∙
10/02/2019
Unsupervised Doodling and Painting with Improved SPIRAL
We investigate using reinforcement learning agents as generative models ...
research
∙
05/30/2019
A Hierarchical Probabilistic U-Net for Modeling Multi-Scale Ambiguities
Medical imaging only indirectly measures the molecular identity of the t...
research
∙
05/22/2019
Data-Efficient Image Recognition with Contrastive Predictive Coding
Large scale deep learning excels when labeled images are abundant, yet d...
research
∙
03/28/2019
Meta-Learning surrogate models for sequential decision making
Meta-learning methods leverage past experience to learn data-driven indu...
research
∙
07/05/2018
Consistent Generative Query Networks
Stochastic video prediction is usually framed as an extrapolation proble...
research
∙
07/04/2018
Encoding Spatial Relations from Natural Language
Natural language processing has made significant inroads into learning t...
research
∙
07/04/2018
Learning models for visual 3D localization with implicit mapping
We propose a formulation of visual localization that does not require co...
research
∙
07/04/2018
Neural Processes
A neural network (NN) is a parameterised function that can be tuned via ...
research
∙
07/04/2018
Conditional Neural Processes
Deep neural networks excel at function approximation, yet they are typic...
research
∙
06/13/2018
A Probabilistic U-Net for Segmentation of Ambiguous Images
Many real-world vision problems suffer from inherent ambiguities. In cli...
research
∙
04/25/2018
Generative Temporal Models with Spatial Memory for Partially Observed Environments
In model-based reinforcement learning, generative and temporal models of...
research
∙
04/03/2018
Synthesizing Programs for Images using Reinforced Adversarial Learning
Advances in deep generative networks have led to impressive results in r...
research
∙
03/10/2018
Kickstarting Deep Reinforcement Learning
We present a method for using previously-trained 'teacher' agents to kic...
research
∙
02/21/2018
Machine Theory of Mind
Theory of mind (ToM; Premack & Woodruff, 1978) broadly refers to humans'...
research
∙
02/08/2018
Learning and Querying Fast Generative Models for Reinforcement Learning
A key challenge in model-based reinforcement learning (RL) is to synthes...
research
∙
10/27/2017
Few-shot Autoregressive Density Estimation: Towards Learning to Learn Distributions
Deep autoregressive models have shown state-of-the-art performance in de...
research
∙
07/07/2017
Emergence of Locomotion Behaviours in Rich Environments
The reinforcement learning paradigm allows, in principle, for complex be...
research
∙
07/03/2016
Unsupervised Learning of 3D Structure from Images
A key goal of computer vision is to recover the underlying 3D structure ...
research
∙
03/28/2016
Attend, Infer, Repeat: Fast Scene Understanding with Generative Models
We present a framework for efficient inference in structured image model...
research
∙
03/09/2015
Kernel-Based Just-In-Time Learning for Passing Expectation Propagation Messages
We propose an efficient nonparametric strategy for learning a message op...
research
∙
10/27/2014