🇵🇹 🇱🇹 Building cool stuff online 🚀 https://xitter.cf/t.co/hAM6dKYCZ9 · https://xitter.cf/t.co/LIUHveO4Cp · https://xitter.cf/t.co/cTPFyJLMSX · 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
- Following223
- Followers198
- Likes4K
It's done @MolonLabeVC Avalon Nano 3, freed.
github.com/marceloeatworld/n…
🤐
Humanoid #Robots Take Flight in Coordinated Forest Navigation
by @Fabriziobustama
#Robotics #Innovation #Engineering #Technology #Tech #FutureTech
DataEatsWorld retweeted
If you’re a security researcher doing Bug Bounty in blockchain, don’t waste your time reporting it unless it’s a zero-day with no preconditions that can affect millions of dollars today without much effort. If your vulnerability can’t do that, good luck getting a decent bounty honestly even zero-days aren’t guaranteed to be properly paid in today’s economy.
DataEatsWorld retweeted
When I said hunch could learn in real-time I wasn't kidding. It's like teaching a kid!
Behind the scenes, @Cloudflare’s Clef is helping refine the local model so it learns in real time, while @googlegemma’s EmbeddingGemma2 runs live on the CPU. 🧵
It's been a while since I showed any Jev stuff but I've been cooking on a way to use @GoogleDeepMind's EmbeddingGemma2 as an insanely fast real-time /v1/systemone endpoint (20ms on text, 100ms on images).
It's trainable in real-time, can distill an upstream teacher model, and is multi-modal by default. Hard to believe a @googlegemma model of this size can do so well with the right harness!
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
Building Auditable AI Text Detectors with Sparse Autoencoders
paper: huggingface.co/papers/2610.3…
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/
😂🤣 don't accept the steak please @saylor
