1 citations · 1 across the 7 of their papers we have counts for
7 papers
Teacher Geometry Shapes Learnability in Teacher-Student Networks
Kai J. Sandbrink, Flavio Martinelli, Alexander van Meegen +2
Teacher-student systems, in which a teacher neural network generates training labels so that a student neural network can learn to implement the same function, are widely used as a…
DiG-bench: Discovery in Games
Ruairidh M. Battleday, Kai Sandbrink, Jimi Cullen-Drohan +13
Discovery---formulating novel generalizations---is a central part of the scientific process. Despite its importance, there is a gap in the current AI benchmark landscape, with few…
Pretraining Curricula Enable Selective Fine-tuning
Sebastian A. Bruijns, Jirko Rubruck, Mia H. Whitefield +3
Transformers follow implicit curricula whereby some tasks are learned before others. However, how explicit pretraining curricula influence learning, generalization, and the selecti…
Post-training makes large language models less human-like
Marcel Binz, Elif Akata, Abdullah Almaatouq +76
Large language models (LLMs) are increasingly used as surrogates for human participants, but it remains unclear which models best capture human behavior and why. To address this, w…
Flexible task abstractions emerge in linear networks with fast and bounded units
Kai Sandbrink, Jan P. Bauer, Alexandra M. Proca +3
Animals survive in dynamic environments changing at arbitrary timescales, but such data distribution shifts are a challenge to neural networks. To adapt to change, neural systems m…
Multilevel Interpretability Of Artificial Neural Networks: Leveraging Framework And Methods From Neuroscience
Zhonghao He, Jascha Achterberg, Katie Collins +13
As deep learning systems are scaled up to many billions of parameters, relating their internal structure to external behaviors becomes very challenging. Although daunting, this pro…
Rethinking Out-of-Distribution Detection for Reinforcement Learning: Advancing Methods for Evaluation and Detection
Linas Nasvytis, Kai Sandbrink, Jakob Foerster +2
While reinforcement learning (RL) algorithms have been successfully applied across numerous sequential decision-making problems, their generalization to unforeseen testing environm…