
🇵🇹 🇱🇹 Building cool stuff online 🚀 https://xitter.cf/t.co/hAM6dKYCZ9 · https://xitter.cf/t.co/LIUHveO4Cp · https://xitter.cf/t.co/jMp9lZpLq4 · https://xitter.cf/t.co/Fz31z868My · https://xitter.cf/t.co/jnpmQKjuTV · https://xitter.cf/t.co/QCVvhNvDMl · https://xitter.cf/t.co/nvfgVXiGNY
127.0.0.1
Joined May 2023
- Tweets2.6K
- Following220
- Followers196
- Likes4K
DataEatsWorld retweeted
Unlimited OCR 2 🔥 New 3B OCR from @BaiduAI_News
- MIT license
- Unlimited horizon document parsing
- SR SWA attention with nearly constant per step memory & latency
- SOTA on 100 page MarathonDocBench
DataEatsWorld retweeted
Unlimited OCR 2 is now open source. 📖✨
Built for virtually unlimited document parsing, it combines Sparse Reference Sliding Window Attention (SR-SWA) with Unlimited-Horizon Decoding to focus computation on the most relevant visual references while releasing KV caches that are no longer needed.
Here’s what it delivers:
• Nearly constant per-step decoding latency and memory footprint as documents grow
• State-of-the-art results on MPDocBench and MarathonDocBench
• On 100-page documents, 7.0× faster per-step decoding than Full Attention and 5.6× faster than R-SWA, with strong parsing accuracy maintained on documents up to 300 pages
Explore it on GitHub. 👇
github.com/baidu/Unlimited-O…
DataEatsWorld retweeted
Unlimited OCR 2 is here, and it's open source. 📖 ✨
Longer documents can mean a lot more attention computation. Our new SR-SWA mechanism keeps that in check by condensing text-visual attention interactions into a fixed-size set of working references.
Here's what it delivers:
- Document parsing at virtually any length, within a finite context window
- Nearly constant per-step decoding latency and memory footprint as documents grow longer
- State-of-the-art performance on MPDocBench and MarathonDocBench, covering documents from dozens to hundreds of pages
Check out the model here ↓
DataEatsWorld retweeted
JUST IN: 🇷🇺🇺🇸 Russia says it is ready to supply unlimited diesel to the United States.
DataEatsWorld retweeted
Tailworm. We have zero-trust in our infrastructure. (Tailscale audit) tailworm.com/
Clean water
Replying to @BRICSinfo
What does the EU have that India doesn't? The EU gets access to 1.4 billion potential customers...what does India get?
😂🤣 don't accept the steak please @saylor
$31,500.
This summer's AI reading at API prices. I paid a monthly @claudeai subscription.
77,987 archive pages. 25B+ tokens. 479 people, back to a 1666 baptism.
Claude Code on a VPS, driven from my phone. No OCR: it reads 17th-century handwriting.
aiteklabs.com/blog/reading-p…
My great-grandfather composed 110 works. Nobody in my family had ever heard one.
@claudeai read his handwritten scores with vision, note by note, into ABC notation, then MIDI, then audio.
His Adagio: 160 bars. His own pencilled count: 160.
Listen: family.aiteklabs.com/
DataEatsWorld retweeted
🚨 Orange (AS3215) in #France is experiencing a mobile network outage since 09:30 UTC on October 21. #Internet
Follow the latest on Cloudflare Radar: radar.cloudflare.com/explore…





























