1

When Your AIs Deceive You: Challenges of Partial Observability in Reinforcement Learning from Human Feedback
We theoretically and empirically study safety issues of using RLHF with human evaluators that have limited information
Leon Lang, Davis Foote, Stuart Russell, Anca Dragan, Erik Jenner, Scott Emmons
Cite arXiv Reviews Video Blogpost Podcast TAIS 2024 Poster
When Your AIs Deceive You: Challenges of Partial Observability in Reinforcement Learning from Human Feedback
Evaluating Shutdown Avoidance of Language Models in Textual Scenarios
We analyze in textual scenarios whether language models show the instrumental reasoning to avoid shutdown
Teun van der Weij, Simon Lermen, Leon Lang
Last updated on Jul 3, 2023
Cite arXiv
Evaluating Shutdown Avoidance of Language Models in Textual Scenarios
A Program to Build E(N)-Equivariant Steerable CNNs
We propose a general method to implement equivariant convolutional neural networks and demonstrate it for 3D equivariant tasks. The implementation is based on the Wigner-Eckart theorem for steerable kernels.
Gabriele Cesa, Leon Lang, Maurice Weiler
Cite Reviews + Paper Code
A Program to Build E(N)-Equivariant Steerable CNNs
A Wigner-Eckart Theorem for Group Equivariant Convolution Kernels
We generalize the famous Wigner-Eckart theorem from quantum mechanics in order to characterize steerable kernel spaces in representation theoretic terms.
Leon Lang, Maurice Weiler
Cite arXiv Reviews Video Slides Poster
A Wigner-Eckart Theorem for Group Equivariant Convolution Kernels
Learning to Request Guidance in Emergent Communication
We analyze the training behaviour of an agent that can ask for help. Doing this is costly, and so the agent learns to become more independent in familiar situations.
Benjamin Kolb, Leon Lang, Henning Bartsch, Arwin Gansekoele, Raymond Koopmanschap, Leonardo Romor, David Speck, Mathijs Mul, Elia Bruni
Last updated on Feb 27, 2022
Cite arXiv Proceedings
Learning to Request Guidance in Emergent Communication