👋 Open to Work

cuicheng

ChengCui

·

AI & ML interests

VLM; OCR; AI Data Infra

Recent Activity

upvoted a collection 1 day ago

liked a model 1 day ago

moonshotai/Kimi-K3

liked a model 7 days ago

PaddlePaddle/korean_PP-OCRv5_mobile_rec

View all activity

Organizations

upvoted a collection 1 day ago

Kimi K3

Open Frontier Intelligence • 1 item • Updated 1 day ago • 65

upvoted a paper 7 days ago

HPD-Parsing: Hierarchical Parallel Document Parsing

Paper • 2607.18839 • Published 8 days ago • 11

upvoted 2 papers 21 days ago

RT-DocLayout: Real-Time End-to-End Document Layout Analysis with Reading Order in the Wild

Paper • 2606.23344 • Published Jun 22 • 1

PP-DocLayout: A Unified Document Layout Detection Model to Accelerate Large-Scale Data Construction

Paper • 2503.17213 • Published Mar 21, 2025 • 2

upvoted a paper about 1 month ago

Unlimited OCR Works

Paper • 2606.23050 • Published Jun 22 • 71

upvoted an article about 1 month ago

Article

PP-OCRv6 on Hugging Face: 50-Language OCR from 1.5M to 34.5M Parameters

PaddlePaddle

•

Jun 22

• 30

upvoted a paper about 1 month ago

PP-OCRv6: From 1.5M to 34.5M Parameters, Surpassing Billion-Scale VLMs on OCR Tasks

Paper • 2606.13108 • Published Jun 11 • 8

upvoted a collection about 2 months ago

PP-OCRv6

From 1.5M to 34.5M Parameters, Surpassing Billion-Scale VLMs on OCR Tasks • 19 items • Updated Jun 15 • 106

upvoted a paper about 2 months ago

PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training

Paper • 2606.03264 • Published Jun 2 • 27

upvoted a collection 2 months ago

PaddleOCR-VL-1.6

Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training • 7 items • Updated 21 days ago • 16

upvoted a paper 2 months ago

Real5-OmniDocBench: A Full-Scale Physical Reconstruction Benchmark for Robust Document Parsing in the Wild

Paper • 2603.04205 • Published Mar 4 • 2

upvoted an article 2 months ago

Article

PaddleOCR 3.5: Running OCR and Document Parsing Tasks with a Transformers Backend

PaddlePaddle

•

May 18

• 39

upvoted a paper 4 months ago

Qianfan-OCR: A Unified End-to-End Model for Document Intelligence

Paper • 2603.13398 • Published Mar 11 • 155

upvoted 2 papers 6 months ago

ERNIE 5.0 Technical Report

Paper • 2602.04705 • Published Feb 4 • 269

PaddleOCR-VL-1.5: Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsing

Paper • 2601.21957 • Published Jan 29 • 23

upvoted a collection 6 months ago

PaddleOCR-VL-1.5

Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsing • 8 items • Updated 21 days ago • 19

upvoted a paper 8 months ago

OmniDocBench: Benchmarking Diverse PDF Document Parsing with Comprehensive Annotations

Paper • 2412.07626 • Published Dec 10, 2024 • 30

upvoted a paper 9 months ago

PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model

Paper • 2510.14528 • Published Oct 16, 2025 • 129

upvoted a collection 10 months ago

PaddleOCR-VL

Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model • 5 items • Updated Feb 11 • 32

upvoted an article 10 months ago

Article

Unleashing the Full Potential of ERNIE4.5 using FastDeploy

baidu

•

Sep 19, 2025

• 11