Seijin Kobayashi

According to our database, Seijin Kobayashi authored at least 22 papers between 2018 and 2025.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2025

Emergent temporal abstractions in autoregressive models enable hierarchical reinforcement learning.

Seijin Kobayashi, Yanick Schimpf, Maximilian Schlegel, Angelika Steger, Maciej Wolczyk, Johannes von Oswald, Nino Scherrer, Kaitlin Maile, Guillaume Lajoie, Blake A. Richards, Rif A. Saurous, James Manyika, Blaise Agüera y Arcas, Alexander Meulemans, João Sacramento

CoRR, December, 2025

Embedded Universal Predictive Intelligence: a coherent framework for multi-agent learning.

Alexander Meulemans, Rajai Nasser, Maciej Wolczyk, Marissa A. Weis, Seijin Kobayashi, Blake A. Richards, Guillaume Lajoie, Angelika Steger, Marcus Hutter, James Manyika, Rif A. Saurous, João Sacramento, Blaise Agüera y Arcas

CoRR, November, 2025

MesaNet: Sequence Modeling by Locally Optimal Test-Time Training.

Johannes von Oswald, Nino Scherrer, Seijin Kobayashi, Luca Versari, Songlin Yang, Maximilian Schlegel, Kaitlin Maile, Yanick Schimpf, Oliver Sieberling, Alexander Meulemans, Rif A. Saurous, Guillaume Lajoie, Charlotte Frenkel, Razvan Pascanu, Blaise Agüera y Arcas, João Sacramento

CoRR, June, 2025

Attention as a Hypernetwork.

Simon Schug, Seijin Kobayashi, Yassir Akram, João Sacramento, Razvan Pascanu

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Learning Randomized Algorithms with Transformers.

Johannes von Oswald, Seijin Kobayashi, Yassir Akram, Angelika Steger

Proceedings of the Thirteenth International Conference on Learning Representations, 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 Agüera y Arcas, João Sacramento

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2024

When can transformers compositionally generalize in-context?

Seijin Kobayashi, Simon Schug, Yassir Akram, Florian Redhardt, Johannes von Oswald, Razvan Pascanu, Guillaume Lajoie, João Sacramento

CoRR, 2024

Weight decay induces low-rank attention layers.

Seijin Kobayashi, Yassir Akram, Johannes von Oswald

Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

Discovering modular solutions that generalize compositionally.

Simon Schug, Seijin Kobayashi, Yassir Akram, Maciej Wolczyk, Alexandra Maria Proca, Johannes von Oswald, Razvan Pascanu, João Sacramento, Angelika Steger

Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023

Meta-Learning via Classifier(-free) Diffusion Guidance.

Elvis Nava, Seijin Kobayashi, Yifei Yin, Robert K. Katzschmann, Benjamin F. Grewe

Trans. Mach. Learn. Res., 2023

Uncovering mesa-optimization algorithms in Transformers.

Johannes von Oswald, Eyvind Niklasson, Maximilian Schlegel, Seijin Kobayashi, Nicolas Zucchet, Nino Scherrer, Nolan Miller, Mark Sandler, Blaise Agüera y Arcas, Max Vladymyrov, Razvan Pascanu, João Sacramento

CoRR, 2023

Gated recurrent neural networks discover attention.

Nicolas Zucchet, Seijin Kobayashi, Yassir Akram, Johannes von Oswald, Maxime Larcher, Angelika Steger, João Sacramento

CoRR, 2023

Would I have gotten that reward? Long-term credit assignment by counterfactual contribution analysis.

Alexander Meulemans, Simon Schug, Seijin Kobayashi, Nathaniel D. Daw, Gregory Wayne

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

2022

Meta-Learning via Classifier(-free) Guidance.

Elvis Nava, Seijin Kobayashi, Yifei Yin, Robert K. Katzschmann, Benjamin F. Grewe

CoRR, 2022

The least-control principle for learning at equilibrium.

Alexander Meulemans, Nicolas Zucchet, Seijin Kobayashi, Johannes von Oswald, João Sacramento

CoRR, 2022

The least-control principle for local learning at equilibrium.

Alexander Meulemans, Nicolas Zucchet, Seijin Kobayashi, Johannes von Oswald, João Sacramento

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Disentangling the Predictive Variance of Deep Ensembles through the Neural Tangent Kernel.

Seijin Kobayashi, Pau Vilimelis Aceituno, Johannes von Oswald

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

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

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Posterior Meta-Replay for Continual Learning.

Christian Henning, Maria R. Cervera, Francesco D'Angelo, Johannes von Oswald, Regina Traber, Benjamin Ehret, Seijin Kobayashi, Benjamin F. Grewe, João Sacramento

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Neural networks with late-phase weights.

Johannes von Oswald, Seijin Kobayashi, João Sacramento, Alexander Meulemans, Christian Henning, Benjamin F. Grewe

Proceedings of the 9th International Conference on Learning Representations, 2021

2020

Economical ensembles with hypernetworks.

João Sacramento, Johannes von Oswald, Seijin Kobayashi, Christian Henning, Benjamin F. Grewe

CoRR, 2020

2018

Wheel Defect Detection With Machine Learning.

Gabriel Krummenacher, Cheng Soon Ong, Stefan Koller, Seijin Kobayashi, Joachim M. Buhmann

IEEE Trans. Intell. Transp. Syst., 2018