PaddlePaddle (@PaddlePaddle) / X

PaddlePaddle

870 posts

PaddlePaddle

@PaddlePaddle

The first independent R&D and Open-Source deep learning platform in China. Powering the ERNIE model family.

Shenzhen, China

paddlepaddle.org.cn/en

Joined September 2022

Pinned
PaddlePaddle
@PaddlePaddle
Jun 12
🚀PP-OCRv6 is officially released！ 🔥PaddleOCR’s new OCR model series scales from 1.5M to 34.5M parameters, bringing stronger accuracy, faster inference, and broader deployment options — from browsers and edge devices to servers. 📊What’s new: 🔸Tiny / Small / Medium models:
45K
PaddlePaddle
@PaddlePaddle
Oct 16, 2025
🚀 PaddleOCR-VL is here! Introducing PaddleOCR-VL (0.9B) — the ultra-compact Vision-Language model that reaches SOTA accuracy across text, tables, formulas, charts & handwriting. Breaking the limits of document parsing!🌍 Powered by: • NaViT dynamic vision encoder • ERNIE
88K
PaddlePaddle
@PaddlePaddle
Jan 3, 2023
PaddleSeg is an easy-to-use image segmentation library with awesome pre-trained model zoo, supporting wide-range of practical tasks in Semantic Segmentation, Interactive Segmentation, Panoptic Segmentation, Image Matting, 3D Segmentation, etc. github.com/PaddlePaddle/P…
966K
PaddlePaddle
@PaddlePaddle
Oct 17, 2025
🔥 Huge milestone! PaddleOCR-VL just hit #1 on Hugging Face Trending — only 20 hours after release! 🚀 Let’s keep pushing the boundaries of document intelligence — come and drop a ❤️ now! A big thank you to our amazing community for the love & support! 👉
PaddlePaddle/PaddleOCR-VL · Hugging Face
From huggingface.co
37K
PaddlePaddle
@PaddlePaddle
Oct 22, 2025
🚀 PaddleOCR-VL Benchmark Series | Episode 1: Complex Layout Decoding In the fast-evolving world of document intelligence, many models shine — but which truly performs in real-world scenarios? 🌍 We benchmarked PaddleOCR-VL against MinerU2.5, MonkeyOCR, and GPT-4o, comparing
15K
PaddlePaddle
@PaddlePaddle
Nov 11, 2025
💥 Now Open-Sourced: ERNIE-4.5-VL-28B-A3B-Thinking! 🧠 Compact model, powerful multimodal reasoning. 💪 Just 3B activated parameters—yet it rivals flagship giants! ✨ Lightweight scale, near-SOTA performance. Vision, redefined. 🔍 Highlights: • Advanced visual-language
14K
PaddlePaddle
@PaddlePaddle
Jun 30, 2025
🚀Excited to announce that the ERNIE 4.5 series models are officially open-sourced today! 🙌ERNIE 4.5 models achieved state-of-the-art performance across multiple text and multimodal benchmarks, especially in instruction following, world knowledge memorization, visual
40K
PaddlePaddle
@PaddlePaddle
Oct 25, 2025
🚀 PaddleOCR-VL Benchmark Series | Episode 2: Multilingual Text Recognition In global document workflows, mixed-language texts often lead to confusion and misreads — especially for low-resource languages. 🌏 📊 Key Insight (Ep.2 – Multilingual Recognition): ✅ PaddleOCR-VL •
8.5K
PaddlePaddle
@PaddlePaddle
Oct 29, 2025
🚀 PaddleOCR-VL Benchmark Ep.3 — Handwriting & Vertical Text ✍️ Handwriting & vertical layouts have long been OCR’s toughest challenge. ✅ PaddleOCR-VL • Excels at Chinese & English handwriting — accurate even with messy strokes. • Flawlessly recognizes vertical text in books
6.4K
PaddlePaddle
@PaddlePaddle
Jan 17, 2023
Announcing our open source collaboration with @huggingface! 🚀 75+ #PaddleNLP models already on the @huggingface Hub 🔥 More awesome #PaddlePaddle models across text, image, audio, video and multi-modalities in the works! Learn more at
Welcome PaddlePaddle to the Hugging Face Hub
From huggingface.co
71K
PaddlePaddle
@PaddlePaddle
Nov 4, 2025
💥 Strong Alliance Alert! PaddleOCR-VL × vLLM 🚀 Two powerhouses join forces to bring you a faster, stronger, and smarter multimodal document understanding experience. ⚡ Huge thanks to our global developer community for your passion and support! 🌍 👉 Experience the
vLLM
@vllm_project
Nov 4, 2025
🔥Highly requested by the community, PaddleOCR-VL is now officially supported on vLLM! 🚀 Check out our recipe for this model to get started!👇docs.vllm.ai/projects/recip…
8.7K
PaddlePaddle
@PaddlePaddle
Nov 1, 2025
🚀 PaddleOCR-VL Document Parsing is now LIVE for Public Beta! 🔥Public Beta: • Individual users: up to 200 pages •Enterprise users: up to 1000 pages 💡Introducing PaddleOCR-VL, the SOTA multimodal document parsing solution — purpose-built for complex document understanding.
11K
PaddlePaddle
@PaddlePaddle
Oct 22, 2025
Wow! PaddleOCR just hit 60K⭐️ on GitHub! A huge milestone — and a big THANK YOU to our amazing developer community! 🙌 ✨ From a high-precision, ultra-lightweight OCR framework → to a global leader in intelligent text recognition 🧠 Powered by PP-OCRv5 & PaddleOCR-VL,
5.8K
PaddlePaddle
@PaddlePaddle
Dec 30, 2022
Happy to share our latest work on #PaddleNLP - 📄 UIE-X 📄 , a multi-modal, multi-task and multilingual Information Extraction engine. 🤗 @Huggingface Space: huggingface.co/spaces/PaddleP… (Thank you for the community GPU grant 😉) A🧵 1/4:huggingface.co/spaces/PaddleP…
48K