Free Lesson
Pushing document parsing frontiers with Reducto
60 min
Oct 14, 2025 2:00 PM
Virtual (Zoom)
In this video
What you'll learn
Hybrid OCR-VLM Architecture Design
Discover how to combine traditional OCR with vision language models to achieve high accuracy and low latency.
Large-Scale Document Processing Pipeline
Learn to build production systems that parse complex multi-page documents without hallucination issues.
Natural Language Document Automation
Master techniques for enabling PDF/Word editing through conversational interfaces and structured extraction.
Why this topic matters
Most business data is trapped in PDFs and Word docs that traditional AI can't reliably process. This hybrid OCR-VLM approach solves a $50B+ problem affecting every industry. Students will learn production-ready techniques to automate document workflows, opening career paths in enterprise AI, fintech, healthcare, and legal tech where document processing expertise commands premium salaries.
You'll learn from

Jason Liu
Consultant at the intersection of Information Retrieval and AI
.png&w=384&q=75)
Evan Vogelbaum
Machine Learning, Reducto
.png&w=384&q=75)
Yifei Hu
Machine Learning, Reducto
.png&w=384&q=75)
Alvin Ryanputra
Engineering, Reducto
worked at
%2520(6).png&w=1536&q=75)