Search – talk-data.com

Title & Speakers	Event
Event 🎄 PyData Berlin 2025 December Meetup 🎄 2025-12-10
A Deep Dive into Program Synthesis: Generating Logic from Examples 2025-12-10 · 18:30 Program Synthesis (PS) is the task of automatically generating logical procedures or source code from a small set of input-output examples. While LLMs and agents dominate current AI conversations, they often struggle with these kinds of precise reasoning tasks—where smaller, well-structured models for PS can succeed. In this talk, we’ll walk through the end-to-end development of an PS system, covering dataset representation using graph structures, model architectures, and tree search algorithms. The working example for this talk is the generation of procedural textures for 3D modeling, but the methodology is domain-agnostic. Participants will leave with a deeper understanding of PS, its real-world potential, and the trade-offs between different architectural approaches. The session is designed for practitioners with a solid understanding of ML concepts and some familiarity with NN architectures such as transformers and CNNs. AI/ML LLM
Building a small end-to-end product with AI: personal learnings and experiences :) 2025-12-10 · 17:00 Jean Carlo Machado – Data Science Manager @ GetYourGuide In this talk, I will walk through how building data products is evolving with modern AI development tools. I’ll take you through a small end-to-end product I built in my free time—covering everything from design, to frontend development, to data collection, and ultimately to building data science components. Here is the link to the project https://stateoftheartwithai.com/ AI/ML Data Collection Data Science

Program Synthesis (PS) is the task of automatically generating logical procedures or source code from a small set of input-output examples. While LLMs and agents dominate current AI conversations, they often struggle with these kinds of precise reasoning tasks—where smaller, well-structured models for PS can succeed. In this talk, we’ll walk through the end-to-end development of an PS system, covering dataset representation using graph structures, model architectures, and tree search algorithms. The working example for this talk is the generation of procedural textures for 3D modeling, but the methodology is domain-agnostic. Participants will leave with a deeper understanding of PS, its real-world potential, and the trade-offs between different architectural approaches. The session is designed for practitioners with a solid understanding of ML concepts and some familiarity with NN architectures such as transformers and CNNs.

talk-data.com

People (5 results)

Activities & events