Google
University of Cambridge
Alexandre PassosMember of Technical Staff · AnthropicResearcher↗
Researcher
Neil Houlsby
AnthropicMember of Technical Staff
Houlsby helped develop the Vision Transformer, showing that an architecture built for language could recognize images by processing them as sequences of patches.[1] He also introduced adapters for language models: small trainable additions that let one model handle new tasks without retraining all its internal weights.[2]
Citation Trend
Total citations to scholarly work, including research papers, technical reports, books and theses, as recorded by Google Scholar. Each point is a dated snapshot.
citations169,386As of Nov 1, '26
citations+5,397Since last snapshot, Oct 1, '26
Selected contributions
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
With Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani and others ·The Vision Transformer recognizes images by treating patches like words in a sequence.
References
- Transformers for Image Recognition at Scaleresearch.google
Official coauthored explanation of vision-patch processing.
- Parameter-Efficient Transfer Learning for NLPproceedings.mlr.press
Adapter method, fixed original network and few new parameters per task.
Based on public sources. If accuracy is important, verify details using the links or references.
For corrections, updates, or requests to remove information, contact us.
Reviewed August 7, 2026 · Checked for accuracy and new information.
