Yannick Metz — accepted AI-conference papers

2026

Learning Reward Functions from Multiple Feedback Types with Amortized Variational Inference

Raphaël Baur, Yannick Metz, Maria Gkoulta, Mennatallah El-Assady, Giorgia Ramponi, Thomas Kleine Buening

ICML 2026poster

Reward learning typically relies on a single feedback type or combines multiple feedback types using manually weighted loss terms. Currently, it remains unclear how to jointly learn reward functions from heterogeneous feedback types such as demonstrations, comparisons, ratings, rankings, and stops t…

Cited by 0 Source ↗Scholar ↗

2025

ResponseRank: Data-Efficient Reward Modeling through Preference Strength Learning

Timo Kaufmann, Yannick Metz, Daniel A. Keim, Eyke Hüllermeier

NeurIPS 2025poster

Binary choices, as often used for reinforcement learning from human feedback (RLHF), convey only the *direction* of a preference. A person may choose apples over oranges and bananas over grapes, but *which preference is stronger*? Strength is crucial for decision-making under uncertainty and general…

Cited by 0 Source ↗Scholar ↗

2025

Reward Learning from Multiple Feedback Types

Yannick Metz, Andras Geiszl, Raphaël Baur, Mennatallah El-Assady

ICLR 2025poster

Learning rewards from preference feedback has become an important tool in the alignment of agentic models. Preference-based feedback, often implemented as a binary comparison between multiple completions, is an established method to acquire large-scale human feedback. However, human feedback in othe…

Cited by 1 Source ↗PDF ↗code ↗Scholar ↗