About

Hi, I’m Frederic. I’m close to finishing my Master’s in Computer Science at the Hasso Plattner Institute in Potsdam. I am currently writing my master’s thesis, which looks at decreasing the prompt sensitivity of language models, under the supervision of Professor Gerard de Melo.

During the summer, I completed a research internship in the Research & Innovation team at SAP in Palo Alto. In this role, I explored agentic collaboration with Professor Diyi Yang from Stanford University.

I am interested in making large language models more robust and efficient, particularly by exploring how information encoded in their latent representations can improve training and generalization. In this area, I have looked into:

• Prompt agnostic LLMs
• Soft prompts
• Hierarchical LLMs
• Efficient BERT models

I have also looked into:

• Collaboration of agents on code tasks
• Reinforcement Learning for Code LLMs

You can find my publications here and my other projects here.