Language, vision, and practical AI .
I build retrieval systems and test visual representations across medical-image datasets.
From contrastive learning to world models.
Nine chapters on collapse prevention, representation geometry, latent prediction, and visual world models.
01 02
A technical roadmap through visual self-supervised learning, from negative-pair contrastive objectives to explicit embedding regularization, latent prediction, and V-JEPA-style world models.
Explore the roadmapSuper-Resolution for Digital Elevation Model Data
A graduation project on enhancing DEM resolution with SRGAN and ESRGAN, using terrain data from Turkiye and Austria.