How do you fine-tune a vision-language model, and what do you freeze?

A VLM is three parts and the interview is entirely about which ones you train. The staged recipe, why the vision encoder almost always stays frozen, and the silent failure where your model learns to answer from the text prior and never looks at the image.

Updated Sep 2026 · Grounded in real GenAI, LLM, and AI/ML engineering interview loops and written to a senior-engineer editorial bar.