UniNote: A Unified Embedding Model for Multimodal Representation and Ranking 事件

UniNote: A Unified Embedding Model for Multimodal Representation and Ranking arXiv:2605.29287v1 Announce Type: cross Abstract: Item-to-Item (I2I) retrieval is a fundamental part of modern content platforms, supporting critical industrial workflows from recommendation engines to content auditing. While multimodal embedding methods have advanced general retrieval, they often falter in I2I scenarios due to the challenges of balancing global content representation with fine-grained local retrieval,