Biography

I am a PhD student at the University of Amsterdam, working on AI safety and previously abstract information theory. In the past, I also worked on equivariant deep learning. You can find my alignment-related blogposts on Lesswrong.

I am searching for research positions in AI Safety, so if you like my profile, please reach out to me via email.

Download my CV.

Interests
  • AI Alignment and Safety
  • Abstract Information Theory
  • Equivariant Deep Learning
Education

  • PhD in AI Safety and Information Theory, 2/2025

    University of Amsterdam

  • MSc in Artificial Intelligence, 8/2020

    University of Amsterdam

  • MSc in Mathematics, 10/2017

    University of Bonn

  • BSc in Mathematics, 8/2015

    University of Heidelberg

Selected Publications

Modeling Human Beliefs about AI Behavior for Scalable Oversight
We explain how modeling human evaluator beliefs about AI behavior can help to better interpret their feedback.
Leon Lang, Patrick Forré
Cite arXiv
Modeling Human Beliefs about AI Behavior for Scalable Oversight
Factored space models: Towards causality between levels of abstraction
We develop a new foundation for a theory of causality, based on factored space models
Scott Garrabrant, Matthias Georg Mayer, Magdalena Wache, Leon Lang, Sam Eisenstat, Holger Dell
Cite arXiv
Factored space models: Towards causality between levels of abstraction
The Perils of Optimizing Learned Reward Functions: Low Training Error Does Not Guarantee Low Regret
We theoretically analyze to what extent an error in a learned reward function translates into regret of resulting policies
Lukas Fluri, Leon Lang, Allesandro Abate, Patrick Forré, David Krueger, Joar Skalse
Cite arXiv
The Perils of Optimizing Learned Reward Functions: Low Training Error Does Not Guarantee Low Regret
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
Abstract Markov Random Fields
We use the recently generalized Hu Theorem to develop a theory of purely abstract Markov random fields.
Leon Lang, Clélia de Mulatier, Rick Quax, Patrick Forré
Cite arXiv
Abstract Markov Random Fields
Information Decomposition Diagrams Applied beyond Shannon Entropy: A Generalization of Hu's Theorem
We generalize information diagrams to functions beyond Shannon entropy, including Kolmogorov complexity and the generalization error from machine learning.
Leon Lang, Pierre Baudot, Rick Quax, Patrick Forré
Cite arXiv Compositionality
Information Decomposition Diagrams Applied beyond Shannon Entropy: A Generalization of Hu's Theorem
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

Blog

Mathematical Writings from my Time as a Student
In this post, I link to unpublished mathematical writings I did when I was a bachelor and master student in mathematics, and a master student in artificial intelligence.
Leon Lang
Mar 6, 2022 1 min read

Contact