Lorenz Wolf

According to our database, Lorenz Wolf authored at least 6 papers between 2022 and 2025.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2025

Reward Model Overoptimisation in Iterated RLHF.

Lorenz Wolf, Robert Kirk, Mirco Musolesi

CoRR, May, 2025

This Is Your Doge, If It Please You: Exploring Deception and Robustness in Mixture of LLMs.

Lorenz Wolf, Sangwoong Yoon, Ilija Bogunovic

CoRR, March, 2025

Private Selection with Heterogeneous Sensitivities.

Daniela Antonova, Allegra Laro, Audra McMillan, Lorenz Wolf

Proceedings of the IEEE Conference on Secure and Trustworthy Machine Learning, 2025

2023

Augmented Modular Reinforcement Learning based on Heterogeneous Knowledge.

Lorenz Wolf, Mirco Musolesi

CoRR, 2023

Energy-Based Models for Functional Data using Path Measure Tilting.

Jen Ning Lim, Sebastian J. Vollmer, Lorenz Wolf, Andrew B. Duncan

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2023

2022

F-EBM: Energy Based Learning of Functional Data.

Jen Ning Lim, Sebastian J. Vollmer, Lorenz Wolf, Andrew B. Duncan

CoRR, 2022