Johannes von Oswald

Transformers learn in-context by gradient descent

Johannes von Oswald, Eyvind Niklasson, Ettore Randazzo et al. · arXiv (Cornell University) · 2022 · 89 citations · Full text

Computing, Computer Science, Artificial Intelligence +16

Learning where to learn: Gradient sparsity in meta and continual learning

Johannes von Oswald, Dominic Zhao, Seijin Kobayashi et al. · Zurich Open Repository and Archive (University of Zurich) · 2021 · 24 citations

Computing, Computer Science, Data Mining +16

Approximating the Predictive Distribution via Adversarially-Trained Hypernetworks

Christian Henning, Johannes von Oswald, João Sacramento et al. · Zurich Open Repository and Archive (University of Zurich) · 2018 · 17 citations

Computing, Computer Science, Artificial Intelligence +15

Learning where to learn: Gradient sparsity in meta and continual\n learning

Johannes von Oswald, Dominic Zhao, Seijin Kobayashi et al. · arXiv (Cornell University) · 2021 · 17 citations · Full text

Computing, Computer Science, Data Mining +16

The least-control principle for local learning at equilibrium

Alexander Meulemans, Nicolas Zucchet, Seijin Kobayashi et al. · arXiv (Cornell University) · 2022 · 15 citations · Full text

Computing, Computer Science, Neuroscience +14