Sort by
Refine Your Search
-
Listed
-
Category
-
Program
-
Learning for Foundation Models’, where the aim is to adapt these models to new tasks without forgetting previous knowledge. The precise focus of the project can be defined in collaboration with
-
), funded by Ministerio de Ciencia, Innovación y Universidades/AEI, focused on ‘Continual Learning for Foundation Models’ where the aim is to adapt foundation models to new tasks without forgetting previous
-
Vision, Language and Reading group at the Computer Vision Center (CVC), in Barcelona, Spain. The position is initially for 3 years and linked to the “European Large Open Multi-Modal Foundation Models
-
datasets. These models, known as Visual Foundation Models (VFMs), encode a kind of universal "visual brains" capable of performing complex visual tasks. The emerging challenge is to harness the power
-
international references in the field. Since 2017, the group has driven advances in end-to-end (sensorimotor) autonomous driving, developing the CIL and CIL++ models that learn directly from human driving
-
on developing new methods for color-specific conditional generation in multi-modal generative models. The candidate will work on exploiting the intrinsic knowledge about color within text-to-image (T2I) models