perception-decoupling

Tag

Cards List
#perception-decoupling

PixelEyes: Decoupling Perception and Reasoning for Pinpoint Visual Evidence Seeking

Hugging Face Daily Papers · 2026-06-30 Cached

PixelEyes proposes a multi-turn visual reasoning agent that decouples perception and reasoning using mask-guided search and semantic-region breadth-first search, introducing a new benchmark (Pinpoint-Bench) and dataset (PixelEyes-6K) to improve localization in visual evidence seeking.

0 favorites 0 likes
← Back to home

Submit Feedback