Paper summary
Paper summary: An Introduction to Vision-Language Modeling
A tutorial-style introduction to vision-language models from a large group of authors: what VLMs are, the main training families, how to train and evaluate them, and the move to video.
- The core difficulty: language is discrete, while vision lives in a much higher-dimensional space where concepts aren't easily discretised.
- The authors present it as an on-ramp for people entering the field.