2.6k citations · 3.3k across the 13 of their papers we have counts for
14 papers
Continuous diffusion for categorical data
Sander Dieleman, Laurent Sartran, Arman Roshannai +11
Diffusion models have quickly become the go-to paradigm for generative modelling of perceptual signals (such as images and sound) through iterative refinement. Their success hinges…
Self-conditioned Embedding Diffusion for Text Generation
Robin Strudel, Corentin Tallec, Florent Altché +8
Can continuous diffusion models bring the same performance breakthrough on natural language they did for image generation? To circumvent the discrete nature of text data, we can si…
A Generalist Neural Algorithmic Learner
Borja Ibarz, Vitaly Kurin, George Papamakarios +12
The cornerstone of neural algorithmic reasoning is the ability to solve algorithmic tasks, especially in a way that generalises out of distribution. While recent years have seen a…
Computer-Aided Design as Language
Yaroslav Ganin, Sergey Bartunov, Yujia Li +2
Computer-Aided Design (CAD) applications are used in manufacturing to model everything from coffee mugs to sports cars. These programs are complex and require years of training and…
PolyGen: An Autoregressive Generative Model of 3D Meshes
Charlie Nash, Yaroslav Ganin, S. M. Ali Eslami +1
Polygon meshes are an efficient representation of 3D geometry, and are of central importance in computer graphics, robotics and games development. Existing learning-based approache…
Unsupervised Doodling and Painting with Improved SPIRAL
John F. J. Mellor, Eunbyung Park, Yaroslav Ganin +7
We investigate using reinforcement learning agents as generative models of images (extending arXiv:1804.01118). A generative agent controls a simulated painting environment, and is…
Synthesizing Programs for Images using Reinforced Adversarial Learning
Yaroslav Ganin, Tejas Kulkarni, Igor Babuschkin +2
Advances in deep generative networks have led to impressive results in recent years. Nevertheless, such models can often waste their capacity on the minutiae of datasets, presumabl…
GibbsNet: Iterative Adversarial Inference for Deep Graphical Models
Alex Lamb, Devon Hjelm, Yaroslav Ganin +3
Directed latent variable models that formulate the joint distribution as have the advantage of fast and exact sampling. However, these models have the w…
DeepWarp: Photorealistic Image Resynthesis for Gaze Manipulation
Yaroslav Ganin, Daniil Kononenko, Diana Sungatullina +1
In this work, we consider the task of generating highly-realistic images of a given face with a redirected gaze. We treat this problem as a specific instance of conditional image g…
Multiregion Bilinear Convolutional Neural Networks for Person Re-Identification
Evgeniya Ustinova, Yaroslav Ganin, Victor Lempitsky
In this work we propose a new architecture for person re-identification. As the task of re-identification is inherently associated with embedding learning and non-rigid appearance…
Domain-Adversarial Training of Neural Networks
Yaroslav Ganin, Evgeniya Ustinova, Hana Ajakan +5
We introduce a new representation learning approach for domain adaptation, in which data at training and test time come from similar but different distributions. Our approach is di…
Speeding-up Convolutional Neural Networks Using Fine-tuned CP-Decomposition
Vadim Lebedev, Yaroslav Ganin, Maksim Rakhuba +2
We propose a simple two-step approach for speeding up convolution layers within large convolutional neural networks based on tensor decomposition and discriminative fine-tuning. Gi…
Unsupervised Domain Adaptation by Backpropagation
Yaroslav Ganin, Victor Lempitsky
Top-performing deep architectures are trained on massive amounts of labeled data. In the absence of labeled data for a certain task, domain adaptation often provides an attractive…
-Fields: Neural Network Nearest Neighbor Fields for Image Transforms
Yaroslav Ganin, Victor Lempitsky
We propose a new architecture for difficult image processing operations, such as natural edge detection or thin object segmentation. The architecture is based on a simple combinati…