Tim Franzmeyer

High Accuracy, Less Talk (HALT): Reliable LLMs through Capability-Aligned Finetuning

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs

Reinforcement Learning for Quantum Control under Physical Constraints

Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs

Scaleable Quantum Control via Physics Constrained Reinforcement Learning