A Global Conversation Series

MachineCollaborators

What happens when researchers work with AI.

About

Researchers I know are already using AI to write code, run analyses, draft papers, and prep for class. Most of them are figuring it out as they go. The interesting question isn't whether they should. It's what happens when they do.

I started Machine Collaborators to make space for that question. Every two weeks, a researcher walks through how AI has actually entered their work, the parts that went well and the parts that didn't, and then we talk about it.

No sales pitches. No policy panels. Just honest conversation about practice.

Next Session

June 25, 2026 · 7:00 PM ET

Steven Denney · Assistant Professor, International Relations and Korean Studies, Leiden University

From Pixels to Patterns: Vision-Language OCR and LLM-Based Text Analysis

Drawing on ongoing research, Steven will walk through a practical pipeline for turning images of text into analyzable data — first using multi-modal and vision-language models to perform OCR, then applying LLM-based reading and classification to extract structure and meaning. The session will cover when vision-language OCR outperforms traditional approaches, how to design prompts and validation steps for downstream text analysis, and what these methods open up for researchers working with archival, multilingual, or otherwise difficult corpora.

Join Zoom Subscribe for Updates