team

Dr. Florian Mai leads the mAI alignment lab, focusing on AI alignment and safety research. His work spans value alignment, reasoning models, and the development of safe large scale AI systems.

Research Interests:

• AI Alignment and Safety
• Value Learning and Preference Modeling
• Reasoning models
• Self-supervised learning
• LLM training

David is a PhD student at the University of Bonn under the supervision of Dr. Florian Mai and Prof. Dr. Lucie Flek since August 2024. His current research interests include emergent misalignment, reinforcement learning, and the training of large language models.

Research Interests:

• Emergent misalignment
• Reinforcement learning in NLP
• Reasoning models
• Training LLMs

Robin is a student assistant at the University of Bonn working with Dr. Florian Mai.

Research Interests:

• Backdoor Detection
• Emergent Misalignment