Region-R1 formulates query image region selection as a reinforcement learning policy optimized with r-GRPO, yielding up to 20% gains in conditional Recall@1 on E-VQA and InfoSeek for multi-modal re-ranking.
You can decide : - If you think a specific region is most relevant to answering the question , select it to focus on it
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Region-R1: Reinforcing Query-Side Region Cropping for Multi-Modal Re-Ranking
Region-R1 formulates query image region selection as a reinforcement learning policy optimized with r-GRPO, yielding up to 20% gains in conditional Recall@1 on E-VQA and InfoSeek for multi-modal re-ranking.