Machine Learning

Machine Learning

The stage dedicated to Machine Learning, focusing on techniques, models, and practical applications in real-world projects.
Here you’ll explore expert insights and case studies to understand how to implement effective ML solutions.

Room Hosting

Roberto Digennaro
Roberto Digennaro
Senior Data Analyst
24 JUNE
25 JUNE
26 JUNE
I Patagarri - Live Concert I Patagarri - Live Concert
Valerio Lundini & I Vazzanikki - Live Concert Valerio Lundini & I Vazzanikki - Live Concert
Dardust - Live Concert Dardust - Live Concert
Ditonellapiaga - Live Concert Ditonellapiaga - Live Concert
N.A.I.P. - Live Concert N.A.I.P. - Live Concert
Opening Ceremony Opening Ceremony
25 june 11:50 - 12:20
30 min
Agents are becoming a new kind of user. They read docs, call tools, run commands, inspect state, and act on someone’s behalf. That changes how software should be built. Using examples from Codex and OpenAI’s plugin ecosystem, Corey Ching will show how to make products useful to agents: when to reach for a skill, MCP server, app, CLI, or a focused combination. The best agent experiences provide the right capabilities that give the agent the missing piece it needs to finish the job.
25 june 12:40 - 13:10
30 min
Building AI agents in regulated industries is not about the model, but the system around it. In this talk we share how we built a scalable RAG pipeline over hundreds of thousands of documents across many data sources, with strong security guardrails, observability and evaluation. We cover architecture decisions, UI/UX tradeoffs for compliance, dynamic interfaces, and how we use user feedback to continuously improve the system.
25 june 14:30 - 15:00
30 min
Generative AI has redefined the user experience at TheFork, revolutionizing how we help people discover their next favorite restaurant. In this talk, we’ll take you behind the scenes of our journey, sharing a filter-free look at how we navigated the complexities of governance, technical challenges, and organizational hurdles. Whether you are a Product Leader or an engineer, you will leave this session with a concrete strategy to integrate GenAI and build products that are not just functional, but truly intelligent.
25 june 15:20 - 15:50
30 min
From monoliths to microservices, and from data centers to the cloud, every wave of digital transformation has reshaped how we build and run technology. Today we stand at the next wave: the shift from apps to agents. Explore how agentic architecture changes system design and see that journey in action through a live demo showcasing how modern agents interact with APIs, tools, and existing systems.
25 june 16:10 - 16:40
30 min
An aligned AI model is trained on a specific task. The result: it begins to behave in risky and unpredictable ways. This is emergent misalignment, a phenomenon we have replicated on real models.Traditional validation strategies are not enough: awareness, continuous evaluation, and red teaming are neededThe goal is to build an understanding of AI Safety: we will present first-hand experimental data and concrete tools for adopting AI without leaving hidden vulnerabilities.
25 june 17:00 - 17:15
15 min
This project presents the methodological architecture and software development of a Computer Vision system optimized for recognizing and classifying highly geometrically complex human poses, using aerial dance as a testing ground and stress-test for predictive models. The objective is to demonstrate how time series of body coordinates can be translated into metric data, enabling the automation of interaction design systems (reactive visuals) and multimodal digital accessibility solutions (audio descriptions).