
ZC
Zijing Cai, Yuzhe Wang, Jingxian Zhu, Fengbin Zhu, Richang Hong
· 1 min read
ResearcharXiv cs.CV
ResComEmb: Effective and Efficient Multimodal Embedding via Residual Homogeneity Compression
arXiv:2609.37225v1 Announce Type: new
Abstract: Multimodal large language models (MLLMs) have shown strong potential for universal multimodal representation learning. However, existing methods either compress each input into a single vector, limiting fine-grained expressiveness, or retain long sequences of visual-token vectors, incurring substantial storage and interaction costs. To resolve this trade-off, we propose ResComEmb, a trainable framework for effective and efficient universal multi-vector multimodal embedding. ResComEmb first encodes each input at native dynamic resolution into ordered global, intermediate, and fine-grained views. After MLLM contextualization and embedding projection, a trainable Residual Homogeneity Compression (RHC) module reduces within-granularity redundancy and cross-granularity repetition under explicit visual token budgets. Then, ResComEmb introduces a length-adaptive Bidirectional Late-Interaction Matching mechanism for robust query-document scoring, which averages the strongest token-level matches in each direction and combines the two scores using a weight based on how many valid tokens each side has. Extensive experiments on MMEB, ViDoRe V1, and ViDoRe V2 show that ResComEmb produces higher-quality universal multimodal embeddings than VLM2Vec-V2, and outperforms ColQwen2.5 in visual document retrieval using only 37.5% of its full visual token budget, demonstrating a favorable effectiveness-efficiency trade-off.
Original source
This story was published by arXiv cs.CV and written by Zijing Cai, Yuzhe Wang, Jingxian Zhu, Fengbin Zhu, Richang Hong. SyncAI.news shows a preview; the complete article is on the publisher's site.
Read the full story on arxiv.org


