Neil Houlsby

From Sparse to Soft Mixtures of Experts ICLR 2024 Frozen Feature Augmentation for Few-Shot Image Classification CVPR 2024 Location-Aware Self-Supervised Transformers for Semantic Segmentation WACV 2024 On Scaling Up a Multilingual Vision and Language Model CVPR 2024 Scaling Laws for Sparsely-Connected Foundation Models ICLR 2024 SciFIBench: Benchmarking Large Multimodal Models for Scientific Figure Interpretation NeurIPS 2024 Adaptive Computation with Elastic Input Sequence ICML 2023 CLIPPO: Image-and-Language Understanding From Pixels Only CVPR 2023 Image Captioners Are Scalable Vision Learners Too NeurIPS 2023 Massively Scaling Heteroscedastic Classifiers ICLR 2023 PaLI: A Jointly-Scaled Multilingual Language-Image Model ICLR 2023 Patch n’ Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution NeurIPS 2023 Scaling Open-Vocabulary Object Detection NeurIPS 2023 Scaling Vision Transformers to 22 Billion Parameters ICML 2023 Sparse Upcycling: Training Mixture-of-Experts from Dense Checkpoints ICLR 2023 Transcending Scaling Laws with 0.1% Extra Compute EMNLP 2023 UL2: Unifying Language Learning Paradigms ICLR 2023 Multimodal Contrastive Learning with LIMoE: the Language-Image Mixture of Experts NeurIPS 2022 Scaling Vision Transformers CVPR 2022 Simple Open-Vocabulary Object Detection with Vision Transformers ECCV 2022 Underspecification Presents Challenges for Credibility in Modern Machine Learning JMLR 2022 UViM: A Unified Modeling Approach for Vision with Learned Guiding Codes NeurIPS 2022 An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale ICLR 2021 MLP-Mixer: An all-MLP Architecture for Vision NeurIPS 2021 On Robustness and Transferability of Convolutional Neural Networks CVPR 2021 Representation Learning From Videos In-the-Wild: An Object-Centric Approach WACV 2021 Revisiting the Calibration of Modern Neural Networks NeurIPS 2021 Scalable Transfer Learning with Expert Models ICLR 2021 Scaling Vision with Sparse Mixture of Experts NeurIPS 2021 Automatic Shortcut Removal for Self-Supervised Representation Learning ICML 2020 Big Transfer (BiT): General Visual Representation Learning ECCV 2020 Self-Supervised Learning of Video-Induced Visual Invariances CVPR 2020 On Self Modulation for Generative Adversarial Networks ICLR 2019 Parameter-Efficient Transfer Learning for NLP ICML 2019 Self-Supervised GANs via Auxiliary Rotation Loss CVPR 2019 Ask the Right Questions: Active Question Reformulation with Reinforcement Learning ICLR 2018 Transfer Learning with Neural AutoML NeurIPS 2018 A Filtering Approach to Stochastic Variational Inference NeurIPS 2014 Cold-start Active Learning with Robust Ordinal Matrix Factorization ICML 2014 Probabilistic Matrix Factorization with Non-random Missing Data ICML 2014 Stochastic Inference for Scalable Probabilistic Modeling of Binary Matrices ICML 2014 Active Learning for Interactive Visualization AISTATS 2013 Collaborative Gaussian Processes for Preference Learning NeurIPS 2012