Home
Blog
Portfolio
Resume
  1. Home
  2. /Blog
  3. /Topics
  4. /OCR

OCR

2 posts tagged OCR.

Apr 26, 2026

Building a Local LLM-Powered Hybrid OCR Engine

How I built a privacy-first, fully offline OCR pipeline that pairs Surya's layout detection with local Vision Language Models (OlmOCR, GLM-OCR, Qwen3-VL) and a Needleman-Wunsch aligner — turning handwriting, forms, and scanned PDFs into pixel-perfect searchable documents on your own laptop.

OCRLLMVision Language Models
12 min read
Building a Local LLM-Powered Hybrid OCR Engine
Feb 25, 2026

From DOI to Markdown: A Two-Repo Pipeline for Faster Research

How DOI Paper Scraper and Papers-to-Markdown work together to convert academic papers into structured Markdown for better reading, search, and research productivity.

Research ProductivityWeb ScrapingOCR
4 min read
From DOI to Markdown: A Two-Repo Pipeline for Faster Research

ME

HomeBlogPortfolioResume

SOCIALS

connect with me:EmailLinkedInGitHubGoogle ScholarORCIDItch.ioArtStationBehance

© 2026 - All Rights Reserved