About
I am a Senior Staff Research Scientist in the Google Brain team, working the Zürich office. I have broad in interests in machine learning and artificial intelligence, with particular focusses on scalable methods, vision, language, and generalization.
Prior to joining Google, I received a PhD from the Cambridge Computational and Biological Learning lab, supervised by Zoubin Ghahramani, and Máté Lengyel. My areas of study were Bayesian ML, active learning, and cognitive science.
I am a hiring manager for the Google Brain Zürich Vision Team, if you have a strong background in Maching Learning and/or Computer Vision, feel free to reach out (fullname@google.com).
Publications
Scaling Vision Transformers
Xiaohua Zhai, Alexander Kolesnikov, Neil Houlsby, Lucas BeyerComputer Vision and Pattern Recognition (CVPR), 2022
[Read here]
Multimodal Contrastive Learning with LIMoE: the Language-Image Mixture of Experts
Basil Mustafa, Carlos Riquelme, Joan Puigcerver, Rodolphe Jenatton, Neil HoulsbyarXiv preprint, 2022
[Read here]
UViM: A Unified Modeling Approach for Vision with Learned Guiding Codes
Alexander Kolesnikov, André Susano Pinto, Lucas Beyer, Xiaohua Zhai, Jeremiah Harmsen, Neil HoulsbyarXiv preprint, 2022
[Read here]
Robust and Efficient Medical Imaging with Self-Supervision
Shekoofeh Azizi, Laura Culp, Jan Freyberg, Basil Mustafa, Sebastien Baur, Simon Kornblith, Ting Chen, Patricia MacWilliams, S. Sara Mahdavi, Ellery Wulczyn, Boris Babenko, Megan Wilson, Aaron Loh, Po-Hsuan Cameron Chen, Yuan Liu, Pinal Bavishi, Scott Mayer McKinney, Jim Winkens, Abhijit Guha Roy, Zach Beaver, Fiona Ryan, Justin Krogue, Mozziyar Etemadi, Umesh Telang, Yun Liu, Lily Peng, Greg S. Corrado, Dale R. Webster, David Fleet, Geoffrey Hinton, Neil Houlsby, Alan Karthikesalingam, Mohammad Norouzi, Vivek NatarajanarXiv preprint, 2022
[Read here]
Simple Open-Vocabulary Object Detection with Vision Transformers
Matthias Minderer, Alexey Gritsenko, Austin Stone, Maxim Neumann, Dirk Weissenborn, Alexey Dosovitskiy, Aravindh Mahendran, Anurag Arnab, Mostafa Dehghani, Zhuoran Shen, Xiao Wang, Xiaohua Zhai, Thomas Kipf, Neil HoulsbyarXiv preprint, 2022
[Read here]
Unifying Language Learning Paradigms
Yi Tay, Mostafa Dehghani, Vinh Q. Tran, Xavier Garcia, Dara Bahri, Tal Schuster, Huaixiu Steven Zheng, Neil Houlsby, Donald MetzlerarXiv preprint, 2022
[Read here]
On the surprising tradeoff between ImageNet accuracy and perceptual similarity
Manoj Kumar, Neil Houlsby, Nal Kalchbrenner, Ekin CubukarXiv preprint, 2022
[Read here]
Learning to Merge Tokens in Vision Transformers
Cedric Renggli, André Susano Pinto, Neil Houlsby, Basil Mustafa, Joan Puigcerver, Carlos RiquelmearXiv preprint, 2022
[Read here]
Comparing Transfer and Meta Learning Approaches on a Unified Few-Shot Classification Benchmark
Vincent Dumoulin, Neil Houlsby, Utku Evci, Xiaohua Zhai, Ross Goroshin, Sylvain Gelly, Hugo LarochelleNeural Information Processing Systems Datasets and Benchmarks Track (NeurIPS), 2021
[Read here]
Scaling Vision with Sparse Mixture of Experts
Carlos Riquelme, Joan Puigcerver, Basil Mustafa, Maxim Neumann, Rodolphe Jenatton, André Susano Pinto, Daniel Keysers, Neil HoulsbyNeural Information Processing Systems (NeurIPS), 2021
[Read here]
MLP-Mixer: An all-MLP Architecture for Vision
Ilya Tolstikhin, Neil Houlsby, Alexander Kolesnikov, Lucas Beyer, Xiaohua Zhai, Thomas Unterthiner, Jessica Yung, Andreas Steiner, Daniel Keysers, Jakob Uszkoreit, Mario Lucic, Alexey DosovitskiyNeural Information Processing Systems (NeurIPS), 2021
[Read here]
Revisiting the Calibration of Modern Neural Networks
Matthias Minderer, Josip Djolonga, Rob Romijnders, Frances Hubis, Xiaohua Zhai, Neil Houlsby, Dustin Tran, Mario LucicNeural Information Processing Systems (NeurIPS), 2021
[Read here]
Sparse MoEs meet Efficient Ensembles
James Urquhart Allingham, Florian Wenzel, Zelda E Mariet, Basil Mustafa, Joan Puigcerver, Neil Houlsby, Ghassen Jerfel, Vincent Fortuin, Balaji Lakshminarayanan, Jasper Snoek, Dustin Tran, Carlos Riquelme Ruiz, Rodolphe JenattonarXiv preprint, 2021
[Read here]
The Benchmark Lottery
Mostafa Dehghani, Yi Tay, Alexey A. Gritsenko, Zhe Zhao, Neil Houlsby, Fernando Diaz, Donald Metzler, Oriol VinyalsarXiv preprint, 2021
[Read here]
On Robustness and Transferability of Convolutional Neural Networks
Josip Djolonga, Jessica Yung, Michael Tschannen, Rob Romijnders, Lucas Beyer, Alexander Kolesnikov, Joan Puigcerver, Matthias Minderer, Alexander D'Amour, Dan Moldovan, Sylvain Gelly, Neil Houlsby, Xiaohua Zhai, Mario LucicComputer Vision and Pattern Recognition (CVPR), 2021
[Read here]
SI-Score: An image dataset for fine-grained analysis of robustness to object location, rotation and size
Jessica Yung, Rob Romijnders, Alexander Kolesnikov, Lucas Beyer, Josip Djolonga, Neil Houlsby, Sylvain Gelly, Mario Lucic, Xiaohua ZhaiInternational Conference on Learning Represenations (2021) RobustML Workshop, 2021
[Read here]
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, Neil HoulsbyInternational Conference on Learning Representations (ICLR), 2021
[Read here]
Scalable Transfer Learning with Expert Models
Joan Puigcerver, Carlos Riquelme, Basil Mustafa, Cedric Renggli, André Susano Pinto, Sylvain Gelly, Daniel Keysers, Neil HoulsbyInternational Conference on Learning Representations (ICLR), 2021
[Read here]
Supervised Transfer Learning at Scale for Medical Imaging
Basil Mustafa, Aaron Loh, Jan Freyberg, Patricia MacWilliams, Megan Wilson, Scott Mayer McKinney, Marcin Sieniek, Jim Winkens, Yuan Liu, Peggy Bui, Shruthi Prabhakara, Umesh Telang, Alan Karthikesalingam, Neil Houlsby, Vivek NatarajanarXiv preprint, 2021
[Read here]
Representation Learning From Videos In-the-Wild: An Object-Centric Approach
Rob Romijnders, Aravindh Mahendran, Michael Tschannen, Josip Djolonga, Marvin Ritter, Neil Houlsby, Mario LucicIEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2021
[Read here]
Underspecification Presents Challenges for Credibility in Modern Machine Learning
Alexander D'Amour, Katherine Heller, Dan Moldovan, Ben Adlam, Babak Alipanahi, Alex Beutel, Christina Chen, Jonathan Deaton, Jacob Eisenstein, Matthew D. Hoffman, Farhad Hormozdiari, Neil Houlsby, Shaobo Hou, Ghassen Jerfel, Alan Karthikesalingam, Mario Lucic, Yian Ma, Cory McLean, Diana Mincu, Akinori Mitani, Andrea Montanari, Zachary Nado, Vivek Natarajan, Christopher Nielson, Thomas F. Osborne, Rajiv Raman, Kim Ramasamy, Rory Sayres, Jessica Schrouff, Martin Seneviratne, Shannon Sequeira, Harini Suresh, Victor Veitch, Max Vladymyrov, Xuezhi Wang, Kellie Webster, Steve Yadlowsky, Taedong Yun, Xiaohua Zhai, D. SculleyarXiv preprint, 2020
[Read here]
Deep Ensembles for Low-Data Transfer Learning
Basil Mustafa, Carlos Riquelme, Joan Puigcerver, André Susano Pinto, Daniel Keysers, Neil HoulsbyarXiv preprint, 2020
[Read here]
Training General Representations for Remote Sensing Using In-Domain Knowledge
Maxim Neumann, Andre Susano Pinto, Xiaohua Zhai, Neil HoulsbyIEEE International Geoscience and Remote Sensing Symposium (IGARSS), 2020
[Read here]
Big Transfer (BiT): General Visual Representation Learning
Alexander Kolesnikov, Lucas Beyer, Xiaohua Zhai, Joan Puigcerver, Jessica Yung, Sylvain Gelly, Neil HoulsbyEuropean Conference on Computer Vision (ECCV), 2020
[Read here]
Automatic Shortcut Removal for Self-Supervised Representation Learning
Matthias Minderer, Olivier Bachem, Neil Houlsby, Michael TschannenInternational Conference on Machine Learning (ICML), 2020
[Read here]
Self-Supervised Learning of Video-Induced Visual Invariances
Michael Tschannen, Josip Djolonga, Marvin Ritter, Aravindh Mahendran, Xiaohua Zhai, Neil Houlsby, Sylvain Gelly, Mario LucicComputer Vision and Pattern Recognition (CVPR), 2020
[Read here]
A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark
Xiaohua Zhai, Joan Puigcerver, Alexander Kolesnikov, Pierre Ruyssen, Carlos Riquelme, Mario Lucic, Josip Djolonga, Andre Susano Pinto, Maxim Neumann, Alexey Dosovitskiy, Lucas Beyer, Olivier Bachem, Michael Tschannen, Marcin Michalski, Olivier Bousquet, Sylvain Gelly, Neil HoulsbyarXiv Preprint, 2019
[Read here]
Self-Supervised GANs via Auxiliary Rotation Loss
Ting Chen, Xiaohua Zhai, Marvin Ritter, Mario Lucic, Neil HoulsbyComputer Vision and Pattern Recognition (CVPR), 2019
[Read here]
Parameter-Efficient Transfer Learning for NLP
Neil Houlsby, Andrei Giurgiu, Stanislaw Jastrzebski, Bruna Morrone, Quentin de Laroussilhe, Andrea Gesmundo, Mona Attariyan, Sylvain GellyInternational Conference on Machine Learning (ICML), 2019
[Read here]
On Self Modulation for Generative Adversarial Networks
Ting Chen, Mario Lucic, Neil Houlsby, Sylvain GellyInternational Conference on Learning Representations (ICLR), 2019
[Read here]
Neural Architecture Search Over a Graph Search Space
Stanisław Jastrzębski, Quentin de Laroussilhe, Mingxing Tan, Xiao Ma, Neil Houlsby, Andrea GesmundoarXiv preprint, 2018
[Read here]
Transfer Learning with Neural AutoML
Catherine Wong, Neil Houlsby, Yifeng Lu, Andrea GesmundoNeural Information Processing Systems (NeurIPS), 2018
[Read here]
Ask the Right Questions: Active Question Reformulation with Reinforcement Learning
Christian Buck, Jannis Bulian, Massimiliano Ciaramita, Wojciech Gajewski, Andrea Gesmundo, Neil Houlsby, Wei WangInternational Conference on Learning Representations (ICLR), 2018
[Read here]
A Filtering Approach to Stochastic Variational Inference
Neil Houlsby, David BleiNeural Information Processing Systems (NeurIPS), 2014
[Read here]
Efficient Bayesian Active Learning and Matrix Modelling
Neil HoulsbyDoctor of Philosophy (PhD), University of Cambridge, 2014
[Read here]
Stochastic Inference for Scalable Probabilistic Modeling of Binary Matrices
José Miguel Hernández-Lobato, Neil Houlsby, Zoubin GhahramaniInternational Conference on Machine Learning (ICML), 2014
[Read here]
Probabilistic Matrix Factorization with Non-random Missing Data
José Miguel Hernández-Lobato, Neil Houlsby, Zoubin GhahramaniInternational Conference on Machine Learning (ICML), 2014
[Read here]
Cold-start Active Learning with Robust Ordinal Matrix Factorization
Cold-start Active Learning with Robust Ordinal Matrix FactorizationInternational Conference on Machine Learning (ICML), 2014
[Read here]
A Scalable Gibbs Sampler for Probabilistic Entity Linking
Neil Houlsby, Massimiliano CiaramitaEuropean Conference on Information Retrieval (ECIR), 2014
[Read here]
Statistical Fitting of Undrained Strength Data
Neil Houlsby, Guy HoulsbyGéotechnique, 2013
[Read here]
Cognitive Tomography Reveals Complex Task-Independent Mental Representations
Neil Houlsby, Ferenc Huszár, Mohammad Ghassemi, Gergő Orbán, Daniel Wolpert, Máté LengyelCurrent Biology, 2013
[Read here]
Experimental Adaptive Bayesian Tomography
Konstantin Kravtsov, Stanislav Straupe, Igor Radchenko, Gleb Struchalin, Neil Houlsby, Sergey KulikPhyiscal Review A, 2013
[Read here]
Active learning for Interactive Visualization
Tomoharu Iwata, Neil Houlsby, Zoubin GhahramaniInternational Conference on AI and Statistics (AISTATS), 2013
[Read here]
Collaborative Gaussian Processes for Preference Learning
Neil Houlsby, Ferenc Huszár, Jose M. Hernández-lobato, Zoubin GhahramaniNeural Information Processing Systems (NeurIPS), 2012
[Read here]
Adaptive Bayesian Quantum Tomography
Ferenc Huszár, Neil HoulsbyPhysical Review A, 2012
[Read here]
Bayesian Active Learning for Gaussian Process Classification
Neil Houlsby, Ferenc Huszár, Zoubin Ghahramani, Máté LengyelNIPS Workshop on Bayesian optimization, experimental design and bandits: Theory and applications, 2011
[Read here]