talk-data.com

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.

This talk traces the evolution of AI agents from the ambitious but complex AutoGPT experiment in 2023, through Cursor's gradual "autonomy slider" approach (2023-2025), to the elegant simplicity of Claude Code in 2025. The presentation argues that we've moved from highly complex systems with multiple agents, embeddings, and cloud infrastructure that, while groundbreaking, often struggled with basic tasks, to "The Zen of Claude Code": a simple terminal-based agent that achieves excellent performance by embracing the bitter lesson.

Closing Session

Free-floating carsharing systems struggle to balance vehicle supply and demand, which often results in inefficient fleet distribution and reduced vehicle utilization. This talk explores how data scraping can be used to model vehicle demand and user behavior, enabling targeted incentives to encourage self-balancing vehicle flows.

Using information scraped from a major mobility provider over multiple months, the presentation provides spatiotemporal analyses and machine learning results to determine whether it's practically possible to offer low-friction discounts that lead to improved fleet balance.

Kubeflow is a platform for building and deploying portable and scalable machine learning (ML) workflows using containers on Kubernetes-based systems.

We will code together a simple Kubeflow pipeline, show how to test it locally. As a bonus, we will explore one solution to avoid dependency hell using the modern dependency management tool uv.

When a new requirement appears, whether it's document storage, pub/sub messaging, distributed queues, or even full-text search, Postgres can often handle it without introducing more infrastructure.

This talk explores how to leverage Postgres' native features like JSONB, LISTEN/NOTIFY, queueing patterns and vector extensions to build robust, scalable systems without increasing infrastructure complexity.

You'll learn practical patterns that extend Postgres just far enough, keeping systems simpler, more maintainable, and easier to operate, especially in small to medium projects or freelancing setups, where Postgres often already forms a critical part of the stack.

Postgres might not replace everything forever - but it can often get you much further than you think.

Energy infrastructure is vulnerable to damage by erosion or third party interference, which often takes the form of unsanctioned construction. In this talk we discuss our experiences using deep learning algorithms powered by large foundation models to monitor for changes in bi-temporal very-high resolution satellite imagery.

Managing who can see or do what with your data is a fundamental challenge, especially as applications and data grow in complexity. Traditional role-based systems often lack the granularity needed for modern data platforms. Fine-Grained Authorization (FGA) addresses this by controlling access at the individual resource level. In this 90-minute hands-on tutorial, we will explore implementing FGA using OpenFGA, an open-source authorization engine inspired by Google's Zanzibar. Attendees will learn the core concepts of Relationship-Based Access Control (ReBAC) and get practical experience defining authorization models, writing relationship tuples, and performing authorization checks using the OpenFGA Python SDK. Bring your laptop ready to code to learn how to build secure and flexible permission systems for your data applications.

Clear documentation is crucial for the success of open-source libraries, but it’s often hard to get right. In this talk, I’ll share our experience applying the Diataxis documentation framework to improve two HoloViz ecosystem libraries, hvPlot and Panel. Attendees will come away with practical insights on applying Diataxis and strengthening documentation for their own projects.

In aviation, search isn’t simple—people use abbreviations, slang, and technical terms that make exact matching tricky. We started with just Postgres, aiming for something that worked. Over time, we upgraded: semantic embeddings, reranking. We tackled filter complexity, slow index builds, and embedding updates and much more. Along the way, we learned a lot about making AI search fast, accurate, and actually usable for our users. It’s been a journey—full of turbulence, but worth the landing.

This talk introduces a new and innovative business model supported by a network of digital activists that form a collective force for protecting humanity, enabling digitally aware users to reclaim control over their data.

Docling, an open source package, is rapidly becoming the de facto standard for document parsing and export in the Python community. Earning close to 30,000 GitHub in less than one year and now part of the Linux AI & Data Foundation. Docling is redefining document AI with its ease and speed of use. In this session, we’ll introduce Docling and its features, including usages with various generative AI frameworks and protocols (e.g. MCP).