Picture for Kai Sandbrink

Kai Sandbrink

Flexible task abstractions emerge in linear networks with fast and bounded units

Add code
Nov 06, 2024
Viaarxiv icon

Multilevel Interpretability Of Artificial Neural Networks: Leveraging Framework And Methods From Neuroscience

Add code
Aug 26, 2024
Viaarxiv icon

Rethinking Out-of-Distribution Detection for Reinforcement Learning: Advancing Methods for Evaluation and Detection

Add code
Apr 10, 2024
Viaarxiv icon