POSTDOC POSITION IN MULTIMODAL FOUNDATION MODELS FOR DOCUMENT UNDERSTANDING
hace 4 días
Bellaterra
ph3POSTDOC POSITION IN MULTIMODAL FOUNDATION MODELS FOR DOCUMENT UNDERSTANDING /h3 pWe are seeking a postdoc to join the Vision, Language and Reading group at the Computer Vision Center (CVC), in Barcelona, Spain. /p pThe position is initially for 6 months and linked to the project “Multimodal LLMs for Document Understanding” (MuDocU), funded by the Ministry of Science, Innovation and Universities. The project targets the development of open multimodal models for document understanding, pushing research forward to deal with large-scale input and the explainability, security and privacy of models. /p pResponsibilities include co‑supervising PhD students, working in a team, and demonstrating initiative and independence. /p pQualifications: PhD in machine learning or computer vision, strong publication record in top conferences such as ICDAR, CVPR, ECCV, ICCV, AAAI, NeurIPS; strong background in large language models and experience in document image analysis. Fluency in oral and written English is required. /p /p #J-18808-Ljbffr