OCR in the Foundation Model Era: From Specialist Models to Unified Models
cs.CV
Submitted: 2026-11-03
Updated: 2026-11-03
Code: https://github.com/zhihengli-casia/Awesome-OCR-in-the-Foundation-Model-Era
Terminology
Sources
- General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model
- OCRVerse: Towards Holistic OCR in End-to-End Vision-Language Models
- PP-OCR: A Practical Ultra Lightweight OCR System
- Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes
- SPTS: Single-Point Text Spotting
- OmniParser: A Unified Framework for Text Spotting, Key Information Extraction and Table Recognition
- Nougat: Neural Optical Understanding for Academic Documents
- HunyuanOCR Technical Report
- Visual Text Processing: A Comprehensive Review and Unified Evaluation
- Multimodal Large Language Models for Text-rich Image Understanding: A Comprehensive Review
- SPTS v2: Single-Point Scene Text Spotting
- OmniParser V2: Structured-Points-of-Thought for Unified Visual Text Parsing and Its Generality to Multimodal Large Language Models
- PP-OCRv6: From 1.5M to 34.5M Parameters, Surpassing Billion-Scale VLMs on OCR Tasks
- Docling Technical Report
- HunyuanOCR-1.5: Making Lightweight OCR VLMs Faster and Better
- OvisOCR2 Technical Report
- Qianfan-OCR: A Unified End-to-End Model for Document Intelligence
- DeepSeek-OCR 2: Visual Causal Flow
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs