Tilman Räuker
Co-Director of pivotal-research.org. Also, doing research at unsearch.org.
Selected publications:
Paper: Structured World Representations in Maze-Solving Transformers – accepted at UniReps
Paper: A Configurable Library for Generating and Manipulating Maze Datasets
Paper: Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks – accepted at SaTML 2023
Previous things I did:
AI safety papers I read: @safe_paper (inactive)
Technical AI safety Research Manager at ERA 2023
Participated at ARENA
Master Thesis at LUH AI
On Temporally-Extended Reinforcement Learning in Dynamic Algorithm Configuration
Supervised by Theresa Eimer and Prof. Marius Lindauer
As a hobby, I like designing prints.