We irregularly team up with companies to host hands-on workshops on cutting-edge AI and machine learning topics. Learn practical skills and explore the latest technologies.
A hands-on workshop focused on integrating Knowledge Graphs and Retrieval Augmented Generation (RAG) to enhance Generative AI projects by reducing hallucinations and providing access to reliable data.
Genomics foundation models have emerged as powerful tools to decode the human genome and understand how genetic variants affect disease and traits. In this hands-on workshop, we will provide an overview of how these models learn the regulatory code of the genome, discuss specific models and applications, and get hands-on experience implementing them.
While Large Language Models have demonstrated unprecedented capabilities in reasoning and retrieval, their internal decision-making processes remain largely opaque. As they grow in complexity, treating these models as 'black boxes' is no longer sufficient for building reliable, safe, and transparent systems.
Large Language Models are no longer limited to text - modern AI systems can see, reason across modalities, and act on rich, multimodal inputs. With these new capabilities comes increased complexity: how do we design multimodal agents that reliably understand visual information, integrate it with language, and remain controllable in real-world applications? We explore how to give your AI eyes by engineering powerful multimodal agents using Haystack
Generative AI models have the potential to increase productivity and provide access to data, but they need good context to be truly useful. In this hands-on workshop, you will learn how Knowledge Graphs and Retrieval Augmented Generation (RAG) can help your GenAI projects avoid hallucination and provide access to reliable data.
Building reliable agentic systems requires more than evaluating individual LLM outputs — it demands a systems-level approach to testing, observability, and operations.
In this workshop, we discuss the unique challenges (and solutions) when deploying Deep Learning models to embedded microcontrollers. We’ll cover key differences between embedded vs. server systems, quantization, embedded application anatomy, inference engines, and a step-by-step deployment walkthrough.
For women and underrepresented genders in tech. An interactive session on code LLMs: model architecture, prompt engineering for developers, evaluating generated code, and how JetBrains IDEs integrate these models. Foundational Python recommended; bring your laptop.
While LLMs make hypothesis generation cheap, current systems still struggle to connect evidence across papers, domains, and mechanisms in a structured and reusable way. We use Cognee to ingest scientific literature, construct graph-based representations of papers and claims, and evaluate candidate hypotheses with explicit graph- and vector-based metrics.
A hands-on workshop on using LLMs as 'heuristic scientists' for open-ended algorithm discovery: generating candidate strategies, turning ideas into executable code, evaluating them with simulations or benchmarks, and refining them through feedback. Participants will build their own small discovery loop and explore the trade-offs between creativity and control, exploration and verification, automation and human judgment.
A hands-on session transitioning from theory to practice by building a custom AI agent. Start with language model APIs, then create an agent that automates complex document workflows—equipping a model with tools to write, compile, and iteratively fix layout issues in markup code.
Digital pathology turns stained tissue slides into gigapixel images — a uniquely demanding frontier for machine learning. Aignostics walks you from core ML research to real-world application: digital pathology fundamentals, building robust pathology foundation models, and hands-on tumor microenvironment profiling with OpenTME and TME Studio.
