2014 · Computer vision
Very Deep Convolutional Networks for Large-Scale Image Recognition
Selected research in computer vision. Read the full paper, including the methods, experiments, and reported results.
Paper & contextKaren Simonyan
Computer vision
Studying deep architectures for visual and language modeling.
Simonyan’s coauthored work spans deep visual architectures and large language models. The selection connects VGG and spatial transformers with multimodal learning and compute-efficient training, showing how architectural ideas carry across research areas.
Selected work
10 papers
2015 · Computer vision
Spatial Transformer Networks
Selected research in computer vision. Read the full paper, including the methods, experiments, and reported results.
Paper & context2022 · Scaling laws
Training Compute-Optimal Large Language Models
The Chinchilla study revisits how to divide a training budget between model size and data. It argues that many contemporary large models were undertrained.
Paper & context2021 · AI for science
Scaling Language Models: Methods, Analysis & Insights from Training Gopher
Selected research in ai for science, language models. Read the full paper, including the methods, experiments, and reported results.
Paper & context2022 · Language models
Flamingo: a Visual Language Model for Few-Shot Learning
Selected research in language models, computer vision. Read the full paper, including the methods, experiments, and reported results.
Paper & context2022 · Language models
HiP: Hierarchical Perceiver
Selected research in language models, computer vision. Read the full paper, including the methods, experiments, and reported results.
Paper & context2022 · Language models
Unified Scaling Laws for Routed Language Models
Selected research in language models, computer vision. Read the full paper, including the methods, experiments, and reported results.
Paper & context2021 · Language models
Improving language models by retrieving from trillions of tokens
Selected research in language models, computer vision. Read the full paper, including the methods, experiments, and reported results.
Paper & context2021 · Language models
Machine Translation Decoding beyond Beam Search
Selected research in language models, computer vision. Read the full paper, including the methods, experiments, and reported results.
Paper & context2021 · Computer vision
Skillful Precipitation Nowcasting using Deep Generative Models of Radar
Selected research in computer vision. Read the full paper, including the methods, experiments, and reported results.
Paper & contextAn independent editorial profile. Inclusion does not imply Council membership or endorsement. Research is collaborative; coauthorship does not imply sole credit.
Selection & sources