AINeutralarXiv – CS AI · Jun 196/10
🧠
ELVA: Exploring Ranking-Driven Universal Multimodal Retrieval
Researchers introduce ELVA, a reinforcement learning framework that improves multimodal retrieval by addressing 'grain blindness'—where models fail to capture fine-grained query details. The approach treats negative samples with varying importance based on similarity and achieves 13.1% improvement on a new MRBench benchmark designed for multi-grain queries.