Why do they do post training instead of just delegating segmentation to a smalle... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		IncreasePosts 7 months ago \| parent \| context \| favorite \| on: Is Gemini 2.5 good at bounding boxes? Why do they do post training instead of just delegating segmentation to a smaller/purpose-built model?

thegeomaster 7 months ago [–]

Post-training allows leveraging the considerable world and language understanding of the underlying pretrained model. Intuition is that this would be a boost to performance.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact