-
reinforcement learning for large language models (LLMs). Research directions include developing next-generation post-training algorithms, exploring diffusion-based approaches to reasoning with language models
-
with ex situ experiments, demographic modelling or handling large datasets as well as holding a valid driver's license is a plus. Application / Contact Please upload your application via our online
-
with large language models (LLMs). The successful candidate will investigate both theoretical aspects – such as understanding the mechanisms and limitations of reasoning in modern LLMs – and practical
-
). Many experimental projects are motivated by theoretical questions, use highly quantitative techniques, and are integrated with theoretical modeling and analysis of the data. Successful candidates should