-
optimization and LLM alignment: design preference-based training and fine-tuning methods (RLHF, PPO, DPO, reward modeling) for medical and multilingual LLMs. Agentic and tool-augmented AI systems: develop
-
of electronic devices has a long and successful history of accompanying experimental developments, be it for transistors or memory cells. Nowadays, to be of practical relevance, such technology computer aided
-
an interest in how psychological theory can improve synthetic data and in deepening our understanding of when and why LLM-generated responses approximate human behavior. The project involves a collaboration
Enter an email to receive alerts for estimation-methods-"https:" positions