PaddlePaddle
@PaddlePaddle
Followers
8K
Following
269
Media
287
Statuses
733
The first independent R&D and Open-Source deep learning platform in China. Powering the ERNIE model family.
Shenzhen, China
Joined September 2022
⚡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 https://t.co/hJqDst8KET
1
0
10
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.
0
3
21
✨ 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. 💡🌏 https://t.co/iOzT9MWETM
#BaiduAI #AI
0
0
7
🚀 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.
1
8
94
💥 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
5
36
245
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
2
1
14
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
1
1
10
💥 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
2
3
24
💥 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
🔥Highly requested by the community, PaddleOCR-VL is now officially supported on vLLM! 🚀 Check out our recipe for this model to get started!👇 https://t.co/ForH3ib4Pg
5
17
156
🌍 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 &
0
3
24
🚀 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.
7
11
143
🚀 Wow — it’s official! PaddleOCR downloads just smashed 10 MILLION+! A huge thank-you to our amazing global community ❤️ Your turn to try it out — let’s make the next 10M happen together! 💪 👉 https://t.co/PQz4nHXMZ3
#PaddleOCR #OpenSource #AI #OCR #BaiduAI
0
0
20
🚀 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
7
19
179
🚀 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 •
4
15
182