Hello, world
First post. A quick tour of every layout primitive on this site.
Vladimir Salnikov
MSc student in Human-Centered AI at DTU, focused on visual computing. My work sits at the intersection of computer vision, multilingual NLP, and the Scandinavian languages — I currently work on post-training Danish foundation models at Aarhus University, and on maritime computer vision at Kravi Analytics in Lund.
This is where I keep notes on what I build — research, projects, and longer write-ups with math and interactive figures when they help.
Latest writing
Selected projects
Scandinavian Instruction-Tuning Datasets
Unified-format instruction-tuning data for Danish, Swedish, Norwegian Bokmål, and Nynorsk.
SMK Image-Text
An image–text dataset built from digitized SMK (Statens Museum for Kunst) artworks, with Danish and English descriptions.
Danish Wikipedia — Image, Caption, Context
First large-scale Danish image–text dataset that preserves neighboring article context, not just a single caption.