Imagen de Portada

Hierarchical Patch Compression for ColPali: Efficient Multi-Vector Document Retrieval with Dynamic Pruning and Quantization

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Bach, Duong
Formato:	Preprint
Publicado:	2025
Materias:	Information Retrieval Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

ColPali: Efficient Document Retrieval with Vision Language Models
por: Faysse, Manuel, et al.
Publicado: (2024)

Structural Anchor Pruning: Training-Free Multi-Vector Compression for Visual Document Retrieval
por: Liu, Zhuchenyang, et al.
Publicado: (2026)

Sculpting the Vector Space: Towards Efficient Multi-Vector Visual Document Retrieval via Prune-then-Merge Framework
por: Yan, Yibo, et al.
Publicado: (2026)

Retrieval-Augmented Search for Large-Scale Map Collections with ColPali
por: Mahowald, Jamie, et al.
Publicado: (2025)

Hybrid-Vector Retrieval for Visually Rich Documents: Combining Single-Vector Efficiency and Multi-Vector Accuracy
por: Kim, Juyeon, et al.
Publicado: (2025)

Video-ColBERT: Contextualized Late Interaction for Text-to-Video Retrieval
por: Reddy, Arun, et al.
Publicado: (2025)

Multi-Vector Index Compression in Any Modality
por: Qin, Hanxiang, et al.
Publicado: (2026)

MIRAGE: Runtime Scheduling for Multi-Vector Image Retrieval with Hierarchical Decomposition
por: Li, Maoliang, et al.
Publicado: (2025)

A Multi-Granularity Retrieval Framework for Visually-Rich Documents
por: Xu, Mingjun, et al.
Publicado: (2025)

Patch-wise Retrieval: A Bag of Practical Techniques for Instance-level Matching
por: Choi, Wonseok, et al.
Publicado: (2025)

ReinPool: Reinforcement Learning Pooling Multi-Vector Embeddings for Retrieval System
por: Cha, Sungguk, et al.
Publicado: (2026)

Fine-grained Motion Retrieval via Joint-Angle Motion Images and Token-Patch Late Interaction
por: Zhang, Yao, et al.
Publicado: (2026)

Compressible and Searchable: AI-native Multi-Modal Retrieval System with Learned Image Compression
por: Luo, Jixiang
Publicado: (2024)

PHPQ: Pyramid Hybrid Pooling Quantization for Efficient Fine-Grained Image Retrieval
por: Zeng, Ziyun, et al.
Publicado: (2021)

Compressing then Matching: An Efficient Pre-training Paradigm for Multimodal Embedding
por: Li, Da, et al.
Publicado: (2025)

Content-based 3D Image Retrieval and a ColBERT-inspired Re-ranking for Tumor Flagging and Staging
por: Jush, Farnaz Khun, et al.
Publicado: (2025)

Visual Late Chunking: An Empirical Study of Contextual Chunking for Efficient Visual Document Retrieval
por: Yan, Yibo, et al.
Publicado: (2026)

Weakly Supervised Deep Hyperspherical Quantization for Image Retrieval
por: Wang, Jinpeng, et al.
Publicado: (2024)

Language-only Efficient Training of Zero-shot Composed Image Retrieval
por: Gu, Geonmo, et al.
Publicado: (2023)

Fetch-A-Set: A Large-Scale OCR-Free Benchmark for Historical Document Retrieval
por: Molina, Adrià, et al.
Publicado: (2024)

Composed Multi-modal Retrieval: A Survey of Approaches and Applications
por: Zhang, Kun, et al.
Publicado: (2025)

A Resource-Efficient Training Framework for Remote Sensing Text--Image Retrieval
por: Zhang, Weihang, et al.
Publicado: (2025)

Attention Grounded Enhancement for Visual Document Retrieval
por: Cui, Wanqing, et al.
Publicado: (2025)

Deep Hashing via Householder Quantization
por: Schwengber, Lucas R., et al.
Publicado: (2023)

REAL-MM-RAG: A Real-World Multi-Modal Retrieval Benchmark
por: Wasserman, Navve, et al.
Publicado: (2025)

Beyond Global Similarity: Towards Fine-Grained, Multi-Condition Multimodal Retrieval
por: Lu, Xuan, et al.
Publicado: (2026)

Identity-Decoupled Anonymization for Visual Evidence in Multi-modal Retrieval-Augmented Generation
por: Cheng, Zehua, et al.
Publicado: (2026)

An Efficient Post-hoc Framework for Reducing Task Discrepancy of Text Encoders for Composed Image Retrieval
por: Byun, Jaeseok, et al.
Publicado: (2024)

MSAM: Multi-Semantic Adaptive Mining for Cross-Modal Drone Video-Text Retrieval
por: Huang, Jinghao, et al.
Publicado: (2025)

MealRec: Multi-granularity Sequential Modeling via Hierarchical Diffusion Models for Micro-Video Recommendation
por: Dong, Xinxin, et al.
Publicado: (2026)

LongVidSearch: An Agentic Benchmark for Multi-hop Evidence Retrieval Planning in Long Videos
por: Yu, Rongyi, et al.
Publicado: (2026)

Global-to-Local or Local-to-Global? Enhancing Image Retrieval with Efficient Local Search and Effective Global Re-ranking
por: Aiger, Dror, et al.
Publicado: (2025)

UNION: A Lightweight Target Representation for Efficient Zero-Shot Image-Guided Retrieval with Optional Textual Queries
por: Le, Hoang-Bao, et al.
Publicado: (2025)

Are We on the Right Way for Assessing Document Retrieval-Augmented Generation?
por: Shen, Wenxuan, et al.
Publicado: (2025)

Benchmarking Retrieval-Augmented Multimodal Generation for Document Question Answering
por: Dong, Kuicai, et al.
Publicado: (2025)

Interactive Multi-Turn Retrieval for Health Videos
por: Wu, Chengzheng, et al.
Publicado: (2026)

Rethinking Sparse Lexical Representations for Image Retrieval in the Age of Rising Multi-Modal Large Language Models
por: Nakata, Kengo, et al.
Publicado: (2024)

Efficient and High-Fidelity Omni Modality Retrieval
por: Huynh, Chuong, et al.
Publicado: (2026)

CoTMR: Chain-of-Thought Multi-Scale Reasoning for Training-Free Zero-Shot Composed Image Retrieval
por: Sun, Zelong, et al.
Publicado: (2025)

Optimizing Multi-Modal Models for Image-Based Shape Retrieval: The Role of Pre-Alignment and Hard Contrastive Learning
por: Kühn, Paul Julius, et al.
Publicado: (2026)