16 citations · 39 across the 10 of their papers we have counts for
12 papers
Otter Weather: Skillful and Computationally Efficient Medium-Range Weather Forecasting
Cristiana Diaconu, Jonas Scholz, Aliaksandra Shysheya +4
State-of-the-art medium-range AI weather models can outperform traditional Numerical Weather Prediction (NWP) but require massive training budgets. This restricts usage for under-r…
JoLT: Joint Probabilistic Predictions on Tabular Data Using LLMs
Aliaksandra Shysheya, John Bronskill, James Requeima +4
We introduce a simple method for probabilistic predictions on tabular data based on Large Language Models (LLMs) called JoLT (Joint LLM Process for Tabular data). JoLT uses the in-…
On conditional diffusion models for PDE simulations
Aliaksandra Shysheya, Cristiana Diaconu, Federico Bergamin +4
Modelling partial differential equations (PDEs) is of crucial importance in science and engineering, and it includes tasks ranging from forecasting to inverse problems, such as dat…
Denoising Diffusion Probabilistic Models in Six Simple Steps
Richard E. Turner, Cristiana-Diana Diaconu, Stratis Markou +3
Denoising Diffusion Probabilistic Models (DDPMs) are a very popular class of deep generative model that have been successfully applied to a diverse range of problems including imag…
Transformer Neural Autoregressive Flows
Massimiliano Patacchiola, Aliaksandra Shysheya, Katja Hofmann +1
Density estimation, a central problem in machine learning, can be performed using Normalizing Flows (NFs). NFs comprise a sequence of invertible transformations, that turn a comple…
Diffusion-Augmented Neural Processes
Lorenzo Bonito, James Requeima, Aliaksandra Shysheya +1
Over the last few years, Neural Processes have become a useful modelling tool in many application areas, such as healthcare and climate sciences, in which data are scarce and predi…
On the Efficacy of Differentially Private Few-shot Image Classification
Marlon Tobaben, Aliaksandra Shysheya, John Bronskill +5
There has been significant recent progress in training differentially private (DP) models which achieve accuracy that approaches the best non-private models. These DP models are ty…
Contextual Squeeze-and-Excitation for Efficient Few-Shot Image Classification
Massimiliano Patacchiola, John Bronskill, Aliaksandra Shysheya +3
Recent years have seen a growth in user-centric applications that require effective knowledge transfer across tasks in the low-data regime. An example is personalization, where a p…
FiT: Parameter Efficient Few-shot Transfer Learning for Personalized and Federated Image Classification
Aliaksandra Shysheya, John Bronskill, Massimiliano Patacchiola +2
Modern deep learning systems are increasingly deployed in situations such as personalization and federated learning where it is necessary to support i) learning on small amounts of…
Fast Bi-layer Neural Synthesis of One-Shot Realistic Head Avatars
Egor Zakharov, Aleksei Ivakhnenko, Aliaksandra Shysheya +1
We propose a neural rendering-based system that creates head avatars from a single photograph. Our approach models a person's appearance by decomposing it into two layers. The firs…
Textured Neural Avatars
Aliaksandra Shysheya, Egor Zakharov, Kara-Ali Aliev +9
We present a system for learning full-body neural avatars, i.e. deep networks that produce full-body renderings of a person for varying body pose and camera position. Our system ta…
Few-Shot Adversarial Learning of Realistic Neural Talking Head Models
Egor Zakharov, Aliaksandra Shysheya, Egor Burkov +1
Several recent works have shown how highly realistic human head images can be obtained by training convolutional neural networks to generate them. In order to create a personalized…