Postdoc Position in Multimodal Models: We are seeking a dedicated postdoctoral researcher to join the Vision, Language, and Reading group at the Computer Vision Center (CVC) in Barcelona, Spain. This position is part of the “European Large Open Multi-Modal Foundation Models For Robust Generalization On Arbitrary Data Streams” (ELLIOT) project funded by Horizon Europe. The successful candidate will focus on developing the next generation of Multimodal Foundation Models applied specifically to Document Understanding.
Postdoc Position in Multimodal Foundation Models for Document Understanding
Designation:
Postdoctoral Researcher
Research Area:
Machine Learning, Computer Vision, Document Image Analysis
Location:
Computer Vision Center (CVC), Barcelona, Spain
Eligibility/Qualification:
- PhD in Machine Learning or Computer Vision
- Strong publication record in top conferences (e.g., ICDAR, CVPR, ECCV, ICCV, AAAI, NeurIPS)
- Background in Large Language Models
- Experience in document image analysis
- Proficiency in oral and written English
- Ability to work collaboratively and independently
- Willingness to co-supervise PhD students
Job Description:
- Participate in large-scale training efforts and research on fine-tuning methods.
- Contribute to the development and application of Multimodal Foundation Models for Document Understanding.
- Collaborate with a talented team of researchers and contribute to the academic community through publications.
- Engage in knowledge transfer and outreach initiatives.
How to Apply:
Interested candidates should submit their applications through the online form, ensuring to include the offer code: 20251002_ELLIOT.
Last Date to Apply:
Open until a suitable candidate is selected.
For more information, please contact:
- Dr. Dimosthenis Karatzas (dimos@cvc.uab.es)
- Dr. Ernest Valveny (ernest@cvc.uab.es)
Join us at the Computer Vision Center and contribute to pioneering research in the field of Document Understanding!