arXiv AI
Spatial Matryoshka Training for Multi-Granularity Visual Document Retrieval
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Jun 9
MM-Matryoshka: Towards Budget-Elastic Visual Document Retrieval via a 2D Multimodal Matryoshka Training Framework
arXiv:2606. 07654v1 Announce Type: cross Abstract: Multi-vector visual document retrievers achieve strong fine-grained matching by representing each page with multiple vectors from deep Vision-Language Models (VLMs), but this design makes deployment expensive in both storage and computational overhead.
arXiv Computer Vision
Sep 21
MAGIC: Marginal-Guided Compression with Optimal Transport for Efficient Visual Document Retrieval
arXiv:2609.21018v1 Announce Type: new Abstract: Recent visual document retrieval (VDR) systems such as ColPali use multi-vector page embeddings, in which patch-level vectors enable fine-grained evide...
arXiv AI
Sep 10
Query-Aware Token Budgeting for Efficient Late-Interaction Visual Document Retrieval
arXiv:2609.07262v1 Announce Type: cross Abstract: Late-interaction visual document retrievers preserve fine-grained page evidence by storing many token embeddings per page, but the resulting storage...
arXiv Computer Vision
Sep 22
AdaMerge: Tuning-Free Patch Compression for Multi-Vector Visual Document Retrieval
arXiv:2609.22562v1 Announce Type: new Abstract: Multi-vector visual document retrieval (VDR) models such as ColPali and ColNomic achieve strong accuracy by representing each document with hundreds to...
arXiv AI
1d ago
ResComEmb: Effective and Efficient Multimodal Embedding via Residual Homogeneity Compression
arXiv:2609.37225v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) have shown strong potential for universal multimodal representation learning. However, existing methods eith...
arXiv Computation and Language
Sep 1
Structural Anchor Pruning: Training-Free Multi-Vector Compression for Visual Document Retrieval
arXiv:2601.20107v3 Announce Type: replace-cross Abstract: Recent Vision-Language Models (e.g., ColPali) enable fine-grained Visual Document Retrieval (VDR) but incur prohibitive multi-vector index st...