Imagen de Portada

Boosting Document Parsing Efficiency and Performance with Coarse-to-Fine Visual Processing

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Cui, Cheng, Sun, Ting, Liang, Suyin, Gao, Tingquan, Zhang, Zelun, Liu, Jiaxuan, Wang, Xueqing, Zhou, Changda, Liu, Hongen, Lin, Manhui, Zhang, Yue, Zhang, Yubo, Zhang, Jing, Zhang, Jun, Wei, Xing, Liu, Yi, Yu, Dianhai, Ma, Yanjun
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition Artificial Intelligence Information Retrieval
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

PaddleOCR-VL-1.5: Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsing
por: Cui, Cheng, et al.
Publicado: (2026)

PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model
por: Cui, Cheng, et al.
Publicado: (2025)

PP-OCRv5: A Specialized 5M-Parameter Model Rivaling Billion-Parameter Vision-Language Models on OCR Tasks
por: Cui, Cheng, et al.
Publicado: (2026)

PaddleOCR 3.0 Technical Report
por: Cui, Cheng, et al.
Publicado: (2025)

Real5-OmniDocBench: A Full-Scale Physical Reconstruction Benchmark for Robust Document Parsing in the Wild
por: Zhou, Changda, et al.
Publicado: (2026)

Doc-Researcher: A Unified System for Multimodal Document Parsing and Deep Research
por: Dong, Kuicai, et al.
Publicado: (2025)

FunnelRAG: A Coarse-to-Fine Progressive Retrieval Paradigm for RAG
por: Zhao, Xinping, et al.
Publicado: (2024)

Boosting Parameter Efficiency in LLM-Based Recommendation through Sophisticated Pruning
por: Zheng, Shanle, et al.
Publicado: (2025)

RoTE: Coarse-to-Fine Multi-Level Rotary Time Embedding for Sequential Recommendation
por: Zhang, Haolin, et al.
Publicado: (2026)

Beyond the Grid: Layout-Informed Multi-Vector Retrieval with Parsed Visual Document Representations
por: Yan, Yibo, et al.
Publicado: (2026)

A Practice-Friendly LLM-Enhanced Paradigm with Preference Parsing for Sequential Recommendation
por: Liu, Dugang, et al.
Publicado: (2024)

System Log Parsing: A Survey
por: Zhang, Tianzhu, et al.
Publicado: (2022)

Coarse-to-Fine Lightweight Meta-Embedding for ID-Based Recommendation
por: Wang, Yang, et al.
Publicado: (2025)

Roles of MLLMs in Visually Rich Document Retrieval for RAG: A Survey
por: Zhang, Xiantao
Publicado: (2025)

MindRec: A Diffusion-driven Coarse-to-Fine Paradigm for Generative Recommendation
por: Gao, Mengyao, et al.
Publicado: (2025)

S2CDR: Smoothing-Sharpening Process Model for Cross-Domain Recommendation
por: Li, Xiaodong, et al.
Publicado: (2026)

ReAlign: Optimizing the Visual Document Retriever with Reasoning-Guided Fine-Grained Alignment
por: Yang, Hao, et al.
Publicado: (2026)

Enhancing Academic Paper Recommendations Using Fine-Grained Knowledge Entities and Multifaceted Document Embeddings
por: Xi, Haixu, et al.
Publicado: (2026)

OmniDocBench: Benchmarking Diverse PDF Document Parsing with Comprehensive Annotations
por: Ouyang, Linke, et al.
Publicado: (2024)

Explainable Coarse-to-Fine Ancient Manuscript Duplicates Discovery
por: Zhang, Chongsheng, et al.
Publicado: (2025)

CART: A Generative Cross-Modal Retrieval Framework with Coarse-To-Fine Semantic Modeling
por: Fang, Minghui, et al.
Publicado: (2024)

GOLFer: Smaller LM-Generated Documents Hallucination Filter & Combiner for Query Expansion in Information Retrieval
por: Liu, Lingyuan, et al.
Publicado: (2025)

GNN-Coder: Boosting Semantic Code Retrieval with Combined GNNs and Transformer
por: Ye, Yufan, et al.
Publicado: (2025)

AFMRL: Attribute-Enhanced Fine-Grained Multi-Modal Representation Learning in E-commerce
por: Zhang, Biao, et al.
Publicado: (2026)

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

NanoVDR: Distilling a 2B Vision-Language Retriever into a 70M Text-Only Encoder for Visual Document Retrieval
por: Liu, Zhuchenyang, et al.
Publicado: (2026)

ETimeline: An Extensive Timeline Generation Dataset based on Large Language Model
por: Liu, Xiaochen, et al.
Publicado: (2025)

Multi-Scenario User Profile Construction via Recommendation Lists
por: Zhang, Hui, et al.
Publicado: (2026)

Fast and Faithful: Real-Time Verification for Long-Document Retrieval-Augmented Generation Systems
por: Liu, Xunzhuo, et al.
Publicado: (2026)

FineRef: Fine-Grained Error Reflection and Correction for Long-Form Generation with Citations
por: Peng, Yixing, et al.
Publicado: (2025)

Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings
por: Ma, Yubo, et al.
Publicado: (2025)

Reinforcement Learning to Rank Using Coarse-grained Rewards
por: Tu, Yiteng, et al.
Publicado: (2022)

FedMM: Federated Collaborative Signal Quantization for Multi-Market CTR Prediction
por: Zhang, Jun, et al.
Publicado: (2026)

SkillPager: Query-Adaptive Intra-Skill Navigation via Semantic Node Retrieval
por: Cui, Zicai, et al.
Publicado: (2026)

CAT-ID$^2$: Category-Tree Integrated Document Identifier Learning for Generative Retrieval In E-commerce
por: Liu, Xiaoyu, et al.
Publicado: (2025)

OkraLong: A Flexible Retrieval-Augmented Framework for Long-Text Query Processing
por: Hui, Yulong, et al.
Publicado: (2025)

CSMF: Cascaded Selective Mask Fine-Tuning for Multi-Objective Embedding-Based Retrieval
por: Deng, Hao, et al.
Publicado: (2025)

Shapley Value-driven Data Pruning for Recommender Systems
por: Zhang, Yansen, et al.
Publicado: (2025)

Boosting Long-Context Management via Query-Guided Activation Refilling
por: Qian, Hongjin, et al.
Publicado: (2024)

An Efficient Pruning Process with Locality Aware Exploration and Dynamic Graph Editing for Subgraph Matching
por: Jiang, Zite, et al.
Publicado: (2021)