Merve Noyan
Bio
Works at Hugging Face open-source team, author of the book Vision Language Models with Hugging Face published by O'Reilly.
Session (1)
Merve Noyan is a developer advocate at Hugging Face focused on open-source multimodal AI and vision-language models. She co-authored the O'Reilly book "Vision Language Models," ships practical tooling (e.g., the smol-vision recipes), and regularly publishes hands-on Hugging Face guides on GUI agents, OCR, and on-device VLMs. Attending her session offers grounded, practitioner-level insight into the current state of open-source multimodal and agentic AI.
Recent talks (4)
GitHub
@merveenoyan- merveenoyan/smol-vision★ 1,948Recipes for shrinking, optimizing, and customizing cutting-edge vision and multimodal AI models
- merveenoyan/my_notes★ 1,653Small cheatsheets covering data science, ML, and computer science topics
- merveenoyan/siglip★ 310Projects based on SigLIP (Zhai et al., 2023) and Hugging Face transformers integration
- merveenoyan/awesome-osml-for-devs★ 197Resource collection for developers building with open-source ML off-the-shelf
Recent writing (3)
- Smol2Operator: Post-Training GUI Agents for Computer Use · blog · Sep 2025
- Supercharge your OCR Pipelines with Open Models · blog · Oct 2025
- Vision Language Models (O'Reilly book) · other · Jun 2026
Public activity researched automatically · as of Jun 2026