Mark Rothermel — accepted AI-conference papers

2025

DEFAME: Dynamic Evidence-based FAct-checking with Multimodal Experts

Tobias Braun, Mark Rothermel, Marcus Rohrbach, Anna Rohrbach

ICML 2025poster

The proliferation of disinformation demands reliable and scalable fact-checking solutions. We present **D**ynamic **E**vidence-based **FA**ct-checking with **M**ultimodal **E**xperts (DEFAME), a modular, zero-shot MLLM pipeline for open-domain, text-image claim verification. DEFAME operates in a six…

Cited by 4 Source ↗PDF ↗code ↗Scholar ↗

2024

Interpretable Concept Bottlenecks to Align Reinforcement Learning Agents

Quentin Delfosse, Sebastian Sztwiertnia, Mark Rothermel, Wolfgang Stammer, Kristian Kersting

NeurIPS 2024poster

Goal misalignment, reward sparsity and difficult credit assignment are only a few of the many issues that make it difficult for deep reinforcement learning (RL) agents to learn optimal policies. Unfortunately, the black-box nature of deep neural networks impedes the inclusion of domain experts for…

Cited by 22 Source ↗PDF ↗code ↗Scholar ↗