PhD Position on Multimodal Foundation Models at the University of Amsterdam’s Video & Image Sense lab

Dive into cutting-edge research on multimodal foundation models, leveraging deep learning and computer vision to develop novel methods for pre-training and fine-tuning multimodal AI models. Balance generalist and specialist approaches to tackle diverse use cases efficiently. Collaborate within the European Horizon ELLIOT project, a 32-partner initiative delivering open foundation models, datasets, and tools for reproducible AI development across Europe.