这篇论文提出了ELVA，用强化学习思路改多模态检索，解决了对比学习忽略粒度的问题，还在新基准MRBench上提了13.1%，值得做检索方向的人看看。
ELVA提出一种基于规则强化学习（RLVR）的框架，解决对比学习在多模态检索中的“粒度盲视”问题——模型忽略查询中的粒度信息。该方法不依赖奖励模型，通过规则奖励联合优化负样本排序并扩大正负样本相似度差距。为精准评估，作者引入新基准MRBench，专用于多粒度查询场景。ELVA在标准检索基准上达到最先进结果，并在MRBench上实现13.1%的提升。
ELVA: Exploring Ranking-Driven Universal Multimodal Retrieval
Leveraging Multimodal Large Language Models (MLLMs) via contrastive learning has become a mainstream paradigm for improving the performance of Universal Multimodal Retrieval (UMR). However, previous works have ignored the grain blindness when adapting the contrastive paradigm into retrieval tasks. Grain blindness refers to the tendency of the model to overlook grain-level information contained in the query, which is crucial for effectively handling complex queries. This stems from contrastive learning treating samples as a binary classification (positive/negative), while ignoring the different information carried by each negative sample. To address this, we argue that negatives should be treated differently according to their similarity to the positive sample, enabling the model to learn distinct grain information from each negative. In this paper, we introduce a simple but effective framework, called ELVA, a novel rule-based RL framework that mitigates grain blindness through ranking-driven MLLMs. 1) Instead of relying on reward models, we extend Reinforcement Learning with Verifiable Rewards (RLVR) to retrieval tasks, allowing the model to explore new ranking behaviors without explicit ranking labels. 2) By utilizing rule-based rewards, our approach jointly optimizes the ranking of negative samples while enlarging the similarity gap between positive and negative. To more precisely measure grain blindness, we further introduce MRBench, a new benchmark specifically designed for multi-grain query scenarios. ELVA achieves state-of-the-art results across standard retrieval benchmarks, and its notable 13.1% improvement on MRBench further demonstrates its effectiveness in alleviating grain blindness.