Linke Ouyang
5 papers · 2024–2026 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Gold
🗺️
Taxonomy Completionist
(16)
🐣
Hot Topic Early Bird
👥
Mega-Team · Legion
Venues
Top co-authors
Research topics
Computer Vision
(4)
Deep Learning
(3)
Machine Learning
(3)
Application Areas
(3)
Domain-Specific
(3)
Artificial Intelligence
(2)
Natural Language Processing
(2)
Applications · Natural Language Processing
(2)
Core AI · Artificial Intelligence
(2)
Models
(2)
Computer Science
(1)
Applications · Computer Science
(1)
Architectures
(1)
Core AI · Computer Vision
(1)
Core Methods
(1)
Keywords
vision-language model
(3)
document understanding
(2)
document parsing
(2)
retrieval-augmented generation
(2)
layout analysis
(2)
image matching
(1)
document analysis
(1)
coarse-to-fine strategy
(1)
evaluation metric
(1)
image understanding
(1)
high resolution
(1)
optical character recognition
(1)
content extraction
(1)
formula recognition
(1)
character detection
(1)
visual matching
(1)
latex rendering
(1)
dynamic resolution
(1)
ocr noise
(1)
large model
(1)
Papers
MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing
ACL 2026
Image Over Text: Transforming Formula Recognition Evaluation with Character Detection Matching
CVPR 2025
OCR Hinders RAG: Evaluating the Cascading Impact of OCR on Retrieval-Augmented Generation
ICCV 2025
OmniDocBench: Benchmarking Diverse PDF Document Parsing with Comprehensive Annotations
CVPR 2025
InternLM-XComposer2-4KHD: A Pioneering Large Vision-Language Model Handling Resolutions from 336 Pixels to 4K HD
NeurIPS 2024