Postdoc: Multimodal LLMs for Document Understanding

Centre de Visio per Computador in Bellaterra, Spain, is seeking a postdoc to join the Vision, Language and Reading group. The role involves research on multimodal LLMs applied to document understanding.

The successful candidate will lead specific project tasks, contribute to top-tier publications, and mentor PhD students. Key qualifications include a PhD (or nearing completion) in machine learning or computer vision, with a strong publication record.