| HyperMixer: An MLP-based Low Cost Alternative to Transformers F Mai, A Pannatier, F Fehr, H Chen, F Marelli, F Fleuret, J Henderson arXiv preprint arXiv:2203.03691, 2022 | 7* | 2022 |
| A VAE for Transformers with Nonparametric Variational Information Bottleneck J Henderson, FJ Fehr International Conference on Learning Representations, 0 | 5* | |
| Hypermixer: An mlp-based low cost alternative to transformers F Mai, A Pannatier, F Fehr, H Chen, F Marelli, F Fleuret, J Henderson arXiv preprint arXiv:2203.03691, 2022 | 4 | 2022 |
| A Variational AutoEncoder for Transformers with Nonparametric Variational Information Bottleneck J Henderson, F Fehr arXiv preprint arXiv:2207.13529, 2022 | 1 | 2022 |
| Nonparametric Variational Regularisation of Pretrained Transformers F Fehr, J Henderson arXiv preprint arXiv:2312.00662, 2023 | | 2023 |
| Learning to Abstract with Nonparametric Variational Information Bottleneck M Behjati, F Fehr, J Henderson arXiv preprint arXiv:2310.17284, 2023 | | 2023 |
| Modelling non-linearity in 3D shapes: A comparative study of Gaussian process morphable models and variational autoencoders for 3D shape data F Fehr Faculty of Science, 2021 | | 2021 |
James HendersonSenior Researcher, Idiap Research InstituteVerified email at idiap.ch
