Publications

For an up-to-date publication list, have a look at my Google Scholar page.

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* Preprint, 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* Preprint, 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 Preprint, 2025

Alexander Meulemans

Publications

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

Emergent temporal abstractions in autoregressive models enable hierarchical reinforcement learning

MesaNet: Sequence Modeling by Locally Optimal Test-Time Training

Multi-agent cooperation through learning-aware policy gradients

Learning probability distributions of sensory inputs with Monte Carlo Predictive Coding

Learning to Extract Structured Entities Using Language Models

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

The least-control principle for learning at equilibrium

Minimizing Control for Credit Assignment with Strong Feedback

Credit Assignment in Neural Networks through Deep Feedback Control

Challenges for Using Impact Regularizers to Avoid Negative Side Effects

Neural networks with late-phase weights

Continual Learning in Recurrent Neural Networks

A Theoretical Framework for Target Propagation