标签
This paper compares natively multimodal embedding models (Gemini Embedding 2, Amazon Nova 2) against frontier LLMs (GPT-4.1, Claude Sonnet 4.6) for hard-negative text-to-image retrieval, finding comparable accuracy but much lower latency for embedding-based ranking.
ECI_sem是一种无需训练的方法，通过使用冻结的嵌入对密集检索中的难负样本源进行排序，在MS MARCO和BEIR基准上取得了强性能。