Eleven AI models graded AR scenes, and the best tracked human raters at 0.87

Eleven AI models graded AR scenes, and the best tracked human raters at 0.87

Six Duke University researchers set eleven commercial vision-language models the job of grading how right augmented reality content looks, and the best of them ordered scenes almost the way people did, at a Spearman rank correlation of 0.8695. The version on arXiv went up on September 30 and is a preprint, though its arXiv entry ... Eleven AI models graded AR scenes, and the best tracked human raters at 0.87 The post Eleven AI models graded AR s…