Kobayashi, Seijin

13 publications

ICLR 2025 Attention as a Hypernetwork Simon Schug, Seijin Kobayashi, Yassir Akram, Joao Sacramento, Razvan Pascanu

ICLR 2025 Learning Randomized Algorithms with Transformers Johannes von Oswald, Seijin Kobayashi, Yassir Akram, Angelika Steger

ICLR 2025 Multi-Agent Cooperation Through Learning-Aware Policy Gradients Alexander Meulemans, Seijin Kobayashi, Johannes von Oswald, Nino Scherrer, Eric Elmoznino, Blake Aaron Richards, Guillaume Lajoie, Blaise Aguera y Arcas, Joao Sacramento

ICLR 2024 Discovering Modular Solutions That Generalize Compositionally Simon Schug, Seijin Kobayashi, Yassir Akram, Maciej Wolczyk, Alexandra Maria Proca, Johannes von Oswald, Razvan Pascanu, Joao Sacramento, Angelika Steger

NeurIPS 2024 Weight Decay Induces Low-Rank Attention Layers Seijin Kobayashi, Yassir Akram, Johannes von Oswald

TMLR 2023 Meta-Learning via Classifier(-Free) Diffusion Guidance Elvis Nava, Seijin Kobayashi, Yifei Yin, Robert K. Katzschmann, Benjamin F Grewe

NeurIPS 2023 Would I Have Gotten That Reward? Long-Term Credit Assignment by Counterfactual Contribution Analysis Alexander Meulemans, Simon Schug, Seijin Kobayashi, Nathaniel Daw, Gregory Wayne

NeurIPS 2022 Disentangling the Predictive Variance of Deep Ensembles Through the Neural Tangent Kernel Seijin Kobayashi, Pau Vilimelis Aceituno, Johannes von Oswald

NeurIPSW 2022 Meta-Learning via Classifier(-Free) Guidance Elvis Nava, Seijin Kobayashi, Yifei Yin, Robert K. Katzschmann, Benjamin F Grewe

NeurIPS 2022 The Least-Control Principle for Local Learning at Equilibrium Alexander Meulemans, Nicolas Zucchet, Seijin Kobayashi, Johannes von Oswald, João Sacramento

NeurIPS 2021 Learning Where to Learn: Gradient Sparsity in Meta and Continual Learning Johannes von Oswald, Dominic Zhao, Seijin Kobayashi, Simon Schug, Massimo Caccia, Nicolas Zucchet, João Sacramento

ICLR 2021 Neural Networks with Late-Phase Weights Johannes von Oswald, Seijin Kobayashi, Joao Sacramento, Alexander Meulemans, Christian Henning, Benjamin F Grewe

NeurIPS 2021 Posterior Meta-Replay for Continual Learning Christian Henning, Maria Cervera, Francesco D'Angelo, Johannes von Oswald, Regina Traber, Benjamin Ehret, Seijin Kobayashi, Benjamin F. Grewe, João Sacramento