#deeplearnjs результаты поиска

🚨 DeepSeek just did something wild. They built an OCR system that compresses long text into vision tokens literally turning paragraphs into pixels. Their model, DeepSeek-OCR, achieves 97% decoding precision at 10× compression and still manages 60% accuracy even at 20×. That…

DeepSeek-OCR looks impressive, but its core idea is not new. Input “Text” as “Image” — already explored by: LANGUAGE MODELING WITH PIXELS (Phillip et al., ICLR 2023) CLIPPO: Image-and-Language Understanding from Pixels Only (Michael et al. CVPR 2023) Pix2Struct: Screenshot…

Builds an OS agent for long-horizon tasks. Uses step-wise RL and self-evolve training to enable the agent to carry out long-horizon interactions. Instead of one big model doing everything, it uses multiple cooperating agents. One for memory and context, one for breaking down…

DeepSeek finally released a new model and paper. And because this DeepSeek-OCR release is a bit different from what everyone expected, and DeepSeek releases are generally a big deal, I wanted to do a brief explainer of what it is all about. In short, they explore how vision…

🚀 DeepSeek-OCR — the new frontier of OCR from @deepseek_ai , exploring optical context compression for LLMs, is running blazingly fast on vLLM ⚡ (~2500 tokens/s on A100-40G) — powered by vllm==0.8.5 for day-0 model support. 🧠 Compresses visual contexts up to 20× while keeping…

Tech giants hoard AI's power. Your prompts trained ChatGPT. Your data built Gemini. Your creativity made DALL-E possible. What did you gain? A bill. A data clause. A thank-you buried in the fine print. You're ready for open, ethical AI. DeepNode is how we build it.

A more serious thread on the DeepSeek-OCR hype / serious misinterpretation going on. 1. On token reduction via representing text in images, researchers from Cambridge have previously shown that 500x prompt token compression is possible (ACL'25, Li, Su, and Collier). Without…

This is the JPEG moment for AI. Optical compression doesn't just make context cheaper. It makes AI memory architectures viable. Training data bottlenecks? Solved. - 200k pages/day on ONE GPU - 33M pages/day on 20 nodes - Every multimodal model is data-constrained. Not anymore.…

👨‍🔧 Inside the smart design of DeepSeek OCR DeepSeek-OCR looks like just another OCR model at first glance, something that reads text from images. But it’s not just that. What they really built is a new way for AI models to store and handle information. Normally, when AI reads…

What if an AI could perform entire data science projects, from raw CSVs to full analytical reports, ALL BY ITSELF? Meet DeepAnalyze, the first agentic LLM built for autonomous data science. Here’s how it works and why it matters 🧵

People are sleeping on Deep Agents. Start using them now. This is a fun paper showcasing how to put together advanced deep agents for enterprise use cases. Uses the best techniques: task decomposition, planning, specialized subagents, MCP for NL2SQL, file analysis, and more.

BOOOOOOOM! CHINA DEEPSEEK DOES IT AGAIN! An entire encyclopedia compressed into a single, high-resolution image! — A mind-blowing breakthrough. DeepSeek-OCR, unleashed an electrifying 3-billion-parameter vision-language model that obliterates the boundaries between text and…

I used to think my prompts were clear. But AI kept missing the point. Every result was close never right. So I started studying *how* it thinks. And that’s when it hit me AI doesn’t understand my words. It understands my structure. That’s why JSON feels so natural to it. It’s…

🚀 Introducing Janus: a revolutionary autoregressive framework for multimodal AI! By decoupling visual encoding & unifying them with a single transformer, it outperforms previous models in both understanding & generation. ⚡️ Powerful, simple, flexible, & next-gen ready! 🔥…

DeepSeek-OCR just dropped. 🔥 Sets a new standard for open-source OCR A 3B-parameter vision-language model designed for high-performance optical character recognition and structured document conversion. - Can parse and re-render charts in HTML - Optical Context Compression:…

Today I explored some deep java script concepts that build the foundation for understanding how code actually runs. 1)Hoisting-how variable and functions are moved to the top during compilation. 2)Memory allocation and execution phase . Scope , closures and HOF.

DeepSeek released an OCR model today. Their motivation is really interesting: they want to use visual modality as an efficient compression medium for textual information, and use this to solve long-context challenges in LLMs. Of course, they are using it to get more training…

I am about understanding this miraculous technology called deep learning. Deep learning is essentially a method for teaching computers to recognize patterns and make decisions by mimicking—loosely—the way our brains process information.

DeepAnalyze is the first agentic LLM for autonomous data science, supporting: 🛠 Data preparation, analysis, modeling, visualization, report generation. 🔍 Data research and produce analyst-grade research reports. Paper: arxiv.org/pdf/2510.16872 Code&Demo: github.com/ruc-datalab/De…