PyData Roma Capitale Meetup @ ELIS Innovation Hub

PyData Roma Capitale Meetup! 🎉
We’re back with a special edition hosted at ELIS, featuring a deep dive into modern Computer Vision and foundation models.
This time we’ll explore how self-supervised learning is reshaping Vision AI, from research breakthroughs to real-world deployment.

If you are working on AI, Computer Vision, edge systems, or simply curious about how large-scale vision models actually work under the hood, this event is for you.

You could be the next speaker for a future event. If you have a presentation, some interesting code, or an open problem you'd like to discuss with the community, compile the form and let us know! (Proposals can be in English or Italian, whatever makes you comfortable.)
Location: Via Sandro Sandri 81
Date: February 26th
Schedule:

• 18:00 🚪 Door Opening
• 18:15 🎤 Talk — Self-supervised Vision at scale: from DINO to DINOv3 and beyond
  Luca Maiano — Founder & CTO @ Synapsi.ai
• 19.15 🤝 Socializing
• 20:30 🔚 Closing

Self-supervised Vision at scale: from DINO to DINOv3 and beyond

Computer vision has long depended on large annotated datasets. But what if models could learn to see without labels?
This talk explores the rise of self-supervised vision through the evolution of DINO to DINOv3. We will unpack the core ideas behind teacher–student training and self-distillation, and understand how modern vision models learn stable, scalable, and dense representations directly from raw pixels.
Finally, we will bridge the gap between research and production. We will discuss the journey of bringing these massive foundation models to the real world, exploring how knowledge distillation allows us to compress DINO’s intelligence into smaller, agile architectures — making foundation-level vision practical for edge devices and real-time applications.

Sign Up!
Space is limited, so RSVP today to secure your spot!
Please note:
Remember to RSVP using your full name for security reasons and bring a valid ID to show at the entrance.
If you can't attend, please let us know at least 2 days in advance so you can free spots for people on the waiting list. We look forward to seeing you there! 🙌