))
DeepSeek-OCR : A Revolutionary Idea
Manage episode 515305446 series 3693358
Dr. Satya Mallick에서 제공하는 콘텐츠입니다. 에피소드, 그래픽, 팟캐스트 설명을 포함한 모든 팟캐스트 콘텐츠는 Dr. Satya Mallick 또는 해당 팟캐스트 플랫폼 파트너가 직접 업로드하고 제공합니다. 누군가가 귀하의 허락 없이 귀하의 저작물을 사용하고 있다고 생각되는 경우 여기에 설명된 절차를 따르실 수 있습니다 https://ko.player.fm/legal.
In this episode, we dive deep into DeepSeek-OCR, a cutting-edge open-source Optical Character Recognition (OCR) / Text Recognition model that's redefining accuracy and efficiency in document understanding.
DeepSeek-OCR flips long-context processing on its head by rendering text as images and then decoding it back—shrinking context length by 7–20× while preserving high fidelity.
We break down how the two-stage stack works—DeepEncoder (optical/vision encoding of pages) + MoE decoder (text reconstruction and reasoning)—and why this "context optical compression" matters for million-token workflows, from legal PDFs to scientific tables.
We also dive into accuracy trade-offs (≈96–97% at ~10× compression), benchmarks, and practical implications for cost, latency, and multimodal RAG. If you care about scaling LLMs beyond brittle token limits, this is the paradigm shift to watch.
Resources:
- DeepSeek-OCR Repo: https://github.com/deepseek-ai/DeepSeek-OCR/tree/main
- DeepSeek-OCR Paper: https://github.com/deepseek-ai/DeepSeek-OCR/blob/main/DeepSeek_OCR_paper.pdf
- Start your AI career: https://opencv.org/university
- Need help in building AI solutions? https://bigvision.ai
6 에피소드
공유
