PaddlePaddle
@PaddlePaddle
The first independent R&D and Open-Source deep learning platform in China. Powering the ERNIE model family.
قد يعجبك
🚀 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…
🔍 PaddleOCR-VL Architecture Explained: Why Two Stages Beat End-to-End Models PaddleOCR-VL stands out in complex document scenarios — and the secret lies in its two-stage “divide & conquer” design. 1️⃣ Stage 1: PP-DocLayoutV2 — Understand the Page First Before recognizing…
ERNIE 5.0 takes multimodality one step further — it reads, sees, listens and reasons as one unified intelligence. Here's a look at how we built our natively omni-modal model ⚡️
Calling all developers! 🚀 The ERNIE AI Developer Challenge is officially LIVE — in collaboration with our amazing ecosystem partners! 👉 bit.ly/485zcq2 🏆 $10,000 cash prizes ⚡ $5,500 in compute, APIs & dev kits Build with the power of ERNIE & PaddlePaddle: ✨…
Wow! 🎉 ERNIE-4.5-VL-28B-A3B Thinking just jumped to #1 on Hugging Face Trending! Thanks to everyone who tried it out — keep the momentum going! 🚀 #BaiduAI #ERNIE #AI
ERNIE-4.5-VL-28B-A3B Thinking model is now the number one trending model on @huggingface 🎉 Huge thanks to everyone in the community who tried it and shared feedback🙌
🚀 FastDeploy 2.3 is here! Now with native support for ERNIE-4.5-VL-28B-A3B-Thinking and PaddleOCR-VL. ⚡ Blazingly fast — up to 30% faster multimodal inference! 🙋 Join our Discord to take part in the new Hands-on Challenge 👉 discord.gg/5dYDFWeb 🔍 Check out our Best…
🚀 PaddleOCR-VL Benchmark Series | Episode 5: Chart Intelligence Charts aren’t just visuals — they’re data. And extracting that data is where true document intelligence shows its power. 📊 Key Insight (Ep.5 – Beyond OCR): ✅ PaddleOCR-VL: Understands bar charts, line charts,…
⚡Still buzzing from #BaiduWorld2025! 🤩 ERNIE keeps leveling up — can’t wait to see what’s next! #ERNIE #BaiduAI
Baidu Unveils ERNIE 5.0 and a Series of AI Applications at Baidu World 2025, Ramps Up Global Push prnewswire.com/news-releases/…
Here comes ERNIE 5.0 — our latest natively omni-modal foundational model. It excels in omni-modal understanding, creative writing, instruction following, and more. We will continue investing in and developing more cutting-edge models to push the boundaries of intelligence.
✨ Every breakthrough begins with a wish — to let knowledge flow, and innovation reach all. #ERNIE #BaiduAI
✨ Welcome to Baidu World 2025! 🚀 Tune in to the live stream and witness how Baidu is shaping the future of AI — smarter, faster, and more connected than ever. 💡🌏 x.com/i/broadcasts/1… #BaiduAI #AI
🚀 PaddleOCR-VL Benchmark Series | Episode 4: Complex Tables & Formulas When structure meets intelligence — tables and formulas reveal the true depth of document understanding. 📄 Key Insight: ✅ PaddleOCR-VL: Accurately reconstructs merged cells, headers, and multi-row logic.…
What a moment! 🎉 ERNIE 5.0 Preview just made it to the top of the Text Arena leaderboard — cheers to the amazing team behind it! 🧠💪 #BaiduAI #ERNIE #AI
🎉We’re thrilled to share that the ERNIE-5.0-Preview-1022 now ranks #2 (tied) globally on the LMArena Text leaderboard — one of the world’s most recognized benchmarks for large language models driven by real-world use. As part of our commitment, we plan to officially release…
ERNIE 5.0 Preview is making waves in the Text Arena! 💥 Onward and upward. 🚀 #ERNIE #BaiduAI #TextArena
🚨Leaderboard Update! A new challenger has stormed the Text Arena, the most competitive field in AI. ERNIE-5.0-Preview-1022 by Baidu @ernieforDevs has reached a score of 1432! The ranking is still preliminary, and we’ll see how it converges. 🔥Huge congrats to the Baidu team…
💥 Manga meets AI! Introducing PaddleOCR-VL-For-Manga, the fine-tuned OCR model that actually understands manga. Trained on Manga109-s & 1.5M synthetic samples, it boosts full-sentence accuracy from 27% → 70%! 🤯 Stylized fonts? Speech bubbles? Full-width madness? This model…
🌍 Bringing China’s AI to the Global Stage! At the “China–Central Asia International Roundtable Forum under the Global Geo-Economic Perspective” hosted by KIMEP University, Kazakhstan 🇰🇿, Chu Xinlei, leader of the PaddlePaddle Navigator Group from Nanjing University of Finance &…
United States الاتجاهات
- 1. Duke 32.2K posts
- 2. Auburn 40.6K posts
- 3. Bama 29.5K posts
- 4. Stockton 23.4K posts
- 5. Miami 133K posts
- 6. Ole Miss 38.5K posts
- 7. Notre Dame 25.7K posts
- 8. Lane Kiffin 48.4K posts
- 9. Stanford 9,835 posts
- 10. #SurvivorSeries 188K posts
- 11. Virginia 48.5K posts
- 12. Austin Theory 5,124 posts
- 13. Cam Coleman 2,011 posts
- 14. #Toonami 3,006 posts
- 15. #JimmySeaFanconD2 161K posts
- 16. Ewing 1,233 posts
- 17. Cooper Flagg 8,426 posts
- 18. Seth 21.4K posts
- 19. #BNewEraBirthdayConcert 500K posts
- 20. The ACC 32.1K posts
قد يعجبك
-
Ultralytics
@ultralytics -
Modal
@modal -
Cohere
@cohere -
BigCode
@BigCodeProject -
Percy Liang
@percyliang -
Yi Tay
@YiTayML -
Law Blocks AI ( $LBT )
@lawblockstoken -
Dr. Daniel Bender
@drdanielbender -
VisitJiangsu
@VisitJiangsu -
ARNORLD PHIRI
@Mumba6Micheal -
Ekin Akyürek
@akyurekekin -
Enrico Shippole
@EnricoShippole -
Josh Long (the JoshMeister)
@theJoshMeister -
睇港澳
@ViewHK_Macao -
Clémentine Fourrier 🍊
@clefourrier
Something went wrong.
Something went wrong.