ResComEmb: Effective and Efficient Multimodal Embedding via Residual Homogeneity Compression
ResComEmb is proposed, a trainable framework for effective and efficient universal multi-vector multimodal embedding that produces higher-quality universal multimodal embeddings than VLM2Vec-V2, and outperforms ColQwen2.5 in visual document retrieval.
Zi-Jing Cai, Yu-Zhe Wang, Jing-Xian Zhu et al.
· 0 citations