Postdoctoral Position in Multi-modal Foundation Models at CVC, Barcelona

Postdoctoral position available at CVC, Barcelona, for research on Multi-modal Foundation Models for Document Understanding as part of the ELLIOT project.

A postdoctoral position is available at the Computer Vision Center (CVC) in Barcelona, Spain, as part of the ‘Vision, Language and Reading’ group. The role is linked to the European ELLIOT project, focusing on developing open Multimodal Foundation Models for tasks like Document Understanding.

Key responsibilities include large-scale training efforts, research on finetuning methods, and applications in Document Understanding. The position is initially for 3 years.

• More information and application: CVC Job Posting
• Contact: Dimosthenis Karatzas (dimos at cvc.uab.es) or Ernest Valveny (ernest at cvc.uab.es)

Tags: Postdoctoral Position, Multi-modal Foundation Models, Document Understanding, Computer Vision Center, ELLIOT Project, Machine Learning, NLP, AI Research