Join us for an exciting deep-dive workshop on On-Device AI with Gemma 3n and PaliGemma 2.

In this session, you’ll explore how modern Vision–Language Models (VLMs) work and how Google’s open models enable powerful on-device inference for real-world use cases. We’ll break down the architecture and capabilities of Gemma 3n and PaliGemma 2, followed by hands-on demonstrations showcasing tasks like image captioning, object detection and OCR, all running directly in the browser.

The workshop will be led by Nitin Tiwari, Google Developer Expert (GDE) in Machine Learning and Lead Data Scientist at Zelar, with extensive experience in AI, ML and Computer Vision.

🔗 Workshop Prerequisites

👉 Please review and complete the prerequisites before the workshop:
https://drive.google.com/file/d/18nWplGSEb5Ya03m6_HKniTtUDzXV-3fH/view?usp=sharing

🎯 Who Can Attend?

This session is open to everyone - students from VESIT as well as other colleges and campuses are welcome.

Whether you’re an AI/ML enthusiast, a developer curious about multimodal models, or someone looking to build efficient on-device AI solutions, this session will give you practical insights and a strong foundation to get started.

✨ Learn how to build smarter, faster and more privacy-friendly AI applications, right on the device.