UniRank: End-to-End Domain-Specific Reranking of Hybrid Text-Image Candidates

ArXi:2603.29897v1 Announce Type: cross Reranking is a critical component in many information retrieval pipelines. Despite remarkable progress in text-only settings, multimodal reranking remains challenging, particularly when the candidate set contains hybrid text and image items. A key difficulty is the modality gap: a text reranker is intrinsically closer to text candidates than to image candidates, leading to biased and suboptimal cross-modal ranking.