Lukas Fluri

Publication Activity (10 Years)

Years Active: 2023-2024
Publications (10 Years): 3

Top Topics

Consistency Checks

Bayesian Inference

Statistical Models

Top Venues

Publications

Lukas Fluri, Daniel Paleka, Florian Tramèr
Evaluating Superhuman Models with Consistency Checks. SaTML (2024)
Lukas Fluri, Leon Lang, Alessandro Abate, Patrick Forré, David Krueger, Joar Skalse
The Perils of Optimizing Learned Reward Functions: Low Training Error Does Not Guarantee Low Regret. CoRR (2024)
Lukas Fluri, Daniel Paleka, Florian Tramèr
Evaluating Superhuman Models with Consistency Checks. CoRR (2023)