3 papers
cs.CL2025
Supervised Fine-Tuning or Contrastive Learning? Towards Better Multimodal LLM Reranking
Ziqi Dai, Xin Zhang, Mingxin Li +6
In information retrieval, training reranking models mainly focuses on two types of objectives: metric learning (e.g. contrastive loss to increase the predicted scores on relevant q…
cs.CL2025
GME: Improving Universal Multimodal Retrieval by Multimodal LLMs
Xin Zhang, Yanzhao Zhang, Wen Xie +7
Universal Multimodal Retrieval (UMR) aims to enable search across various modalities using a unified model, where queries and candidates can consist of pure text, images, or a comb…
cs.CL2025
Towards Text-Image Interleaved Retrieval
Xin Zhang, Ziqi Dai, Yongqi Li +7
Current multimodal information retrieval studies mainly focus on single-image inputs, which limits real-world applications involving multiple images and text-image interleaved cont…