news

Oct 2025 New preprint on Feedback Forensics (web app).
Sep 2025 RtRank accepted at NeurIPS 2025! Our stratified response time ranking approach for data-efficient reward modeling. See you in San Diego!
Jun 2025 Our survey on RLHF is now published by TMLR.
May 2025 Comparing Comparisons accepted at ICML 2025!
Apr 2025 Attended ICLR 2025 in Singapore to present Inverse Constitutional AI. Had a great poster session.
Mar 2025 Check out our recently released feedback forensics, an open-source toolkit for measuring AI personality and analyzing how human feedback affects traits like tone and sycophancy in AI models! (Post)
Mar 2025 Visited my coauthor and friend Arduin Findeis in Cambridge, it’s beautiful.
Dec 2024 DUO paper accepted at AAAI 2025. Our method for diverse and uncertain query selection in RLHF.
Aug 2024 Attended the first RLC in Amherst, MA and presented our OCALM workshop paper. UMass is nice! Poster session.
Jul 2024 Attended ICML in Vienna to present our two workshop papers on distinguishability queries and modeling trainer rationality in human feedback.
Sep 2023 I will present our workshop paper on the challenges and practices of reinforcement learning from real human feedback on the HLDM’23 ECML workshop on Friday next week (September 22nd)!
Apr 2023 I am organizing an invited session on Reinforcement Learning from Human Feedback (RLHF) at ECDA 2023.
Mar 2023 I presented our short-paper at the ML4CPS conference. In the paper we discuss the potential of leveraging self-supervised pretraining for reinforcement learning from human feedback in the context of cyber-physical systems.
Mar 2022 I started my PhD at Eyke Hüllermeier’s AI+ML group at LMU Munich!