CausalEmbed: Auto-Regressive Multi-Vector Generation in Latent Space for Visual Document Embedding

Excerpt

arXiv:2601.21262v4 Announce Type: replace Abstract: Although Multimodal Large Language Models (MLLMs) have shown remarkable potential in Visual Document Retrieval (VDR) through generating high-quality multi-vector embeddings, the substantial storage overhead caused by representing a page with thousands of visual tokens limits their practicality in real-world applications. To address this challenge, we propose an auto-regressive generation approach, CausalEmbed, for constructing multi-vector embe