In Episode 2 of our Give Me 5 series, we talk with Yanina Bellini Saibene"an open source champion whose work embodies what it means to build community to the max. Yanina shares lessons learned from years of uplifting volunteer-driven ecosystems, how she supports contributors and fosters...

   https: guild.host events ia-en-el-sector-pblico-83xu29 PyData Madrid vuelve en diciembre para hablar de Python, Datos, Visualización, Inteligencia Artificial, Y lo que surja Tendremos el placer de contar con dos charlas: El grupo de Inteligencia Artificial de Informática Ayuntamiento de Madrid ...

   This talk presents a practical guide to fine-tuning small language models (SLMs) using powerful open-source Python tools. While large language models (LLMs) are impressive, they often come with steep compute costs, limited domain adaptability, and privacy concerns. By contrast, SLMs offer a leaner,...

   In this talk, we present an admiral-driven machine learning framework for decision-making in marine operations, focusing on how to align algorithmic outputs with human strategic oversight in high-risk environments. The framework leverages metric learning via Inverse Reinforcement Learning (IRL) to...

   Throughout the talk we will give examples from both classic LLM evaluation and their counterparts in the realm of Agents, showcase what not to do, and common pitfalls. This talk provides a practical guide specifically for evaluating these advanced LLM agents, addressing the critical need for...

   In today’s fast-evolving AI landscape, one of the biggest challenges isn’t just learning what to build"but how to learn to build. In this talk, we’ll share our journey of learning how to learn in the world of AI, focusing on understanding the right concepts before jumping into implementation....

   Names are more than labels - they are reflections of our personality, and our background. Where we came from, our culture, heritage, and social values. In that case, names have meanings. Not only the actual meaning of a word, but also the meaning our parents wanted to give us. In this talk, I...

   Everyone is excited about conversational AI. Everyone is implementing their own chatbots, until they have to make a conversation behave in production. Replacing a rigid, quiz-style signup with a dynamic onboarding chat sounds great, but executing it is far from simple. It requires designing a...

   Understanding how data moves through your systems is essential"not just for ensuring data quality, but for responding quickly when things break. In this session, we’ll share how we built a fast, flexible, and low-overhead data lineage tool tailored to our pipelines and team needs....

   We’ll cover the basic idea - how we lived before the LLM vendors let us expclicitly pass the signature of the function (we did prompt engineering) ; how it’s implemented under the hood (it’s prompt engineering all the way down) ; what should someone know when approaching this (use function calling...

   Parliamentary recordings are a hidden goldmine for Hebrew ASR, but they’re also uniquely challenging. The Knesset’s decade-plus of streamed debates contain a variety of technical obstacles, including sessions lasting 50 hours, protocols that preserve the speaker’s "spirit" rather than...

   The journey from a data science prototype to a productionized system can be fraught with challenges, including version control, reliable deployment, and integrating complex logic. This talk addresses these critical pain points by demonstrating how DBT, Python and Snowflake provide a cohesive...

   A model’s performance in a notebook is a promise; production is where that promise is often broken. This is "Notebook Chaos": the silent killer of ML systems where real-world predictions fail because features diverge between training and serving. This session follows the story of...

   Tab-PFN is a recently introduced transformer-based model for classification and regression on tabular data. Published after nearly a decade without significant advances in modeling of such data, it has generated substantial interest due to its promise of exceptional performance across diverse...

   After charting the space of LLM-based systems and establishing a framework around them, I will switch gears to discuss what I see as a huge open-frontier that is enabled by them: a new kind of learning systems, that learn not by optimizing parameters with respect to a numeric loss or reward, but...