Monday: "Introduction to ML/AI"
Michal Hradiš (Brno University of Technology), What is AI? Overview lecture
Claudius Krause (MLA²S, ÖAW), Machine Learning at the ÖAW
Tuesday: Vibe Coding & „Promptotyping”
Christopher Pollin (DH Craft Graz)
This workshop introduces current approaches to AI-assisted software development. Starting with Vibe Coding and Context Engineering, participants will learn the Promptotyping methodology, which enables researchers without programming skills to develop their own data-driven tools and interfaces. Through hands-on exercises, participants will learn to construct with (Frontier-)LLMs and iteratively build functioning research artifacts (tools, models, workflows).
Dr. Christopher Pollin is the founder of Digital Humanities Craft OG and an independent researcher specializing in applied generative AI. He received his PhD from the University of Graz on digital modeling of historical information and is developing the Promptotyping methodology for the systematic creation of research tools using LLMs. He teaches Digital Humanities, Generative AI and Prompt Engineering at several Austrian universities.
Wednesday: "Ethics and AI"
Bernd Wachmann (ÖAW), "The ÖAW AI Strategy"
Patrick Rarivoson, "Open EuroLLM"
Patrick RARIVOSON has done Research studies in both Epistemology, Mathematics & Computer Science. PhD in Epistemology
Started his career both in a Teaching position at Sorbonne University (Greek & Epistemology) and as a System Engineer at Alstom (Embedded Automatic Speed Control for train), doing both Research in Formal specification (maths applied to software specification for automatic consistency proof) and Epistemology (Heidegger & Aristote, about the Economics of Science)
Professional career path includes System Engineering, Business Consulting, and Software Development in Generative AI (current position @ LightOn)
At LightOn, in charge of Funded Projects (tender phase and execution phase) as well as connection between R&D & industrial innovation
Laura Gandlgruber (University of Vienna), "Beyond Tools: Embedding Responsible AI in Teaching and Learning"
This presentation outlines the University of Vienna's AI policy for teaching and learning, demonstrating how the use of artificial intelligence can be institutionally governed and didactically integrated. It covers key areas such as the systematic development of AI competencies for students and teaching staff, the creation of qualification and information resources, and the integration of AI into teaching, learning, and assessment formats. Using concrete measures and implementation examples, the presentation shows how universities can provide clear orientation, safeguard academic integrity, and embed AI as a sustainable component of academic education.
Mag. Dr Laura Gandlgruber, BA, MA, is Programme Manager for Artificial Intelligence in Studies and Teaching at the University of Vienna, as well as being a certified AI manager. She lectures in artificial intelligence and scientific work at the University of Vienna, the FH der WKW, and the University of Vienna's Postgraduate Centre. As an enthusiastic advocate of AI, she keeps up to date with the latest developments in artificial intelligence and its application in teaching, studies and university administration. She designs and leads workshops for teachers and administrative staff, and is also a highly sought-after expert on AI-related topics for events and interviews.
Charlotte Spencer-Smith (CMC), Governing Machines: From Moderation to Alignment
Philip Winter (VRVis), Bias in ML
This talk provides an accessible introduction to bias in machine learning. Beginning with a concise ML crash course that covers key concepts like model training and learning paradigms, we investigate various types of social and technical biases that may occur in modern deep learning applications. Real-world consequences are examined, highlighting societal harms alongside technical pitfalls like reduced generalization and inaccurate predictions. The talk concludes with practical mitigation strategies.
Dr. Philip Winter is a researcher in the fields of Machine Learning and Astrophysics. He studied Astrophysics at University of Vienna (BSc & MSc) and University of Tübingen (Dr), as well as Machine Learning at JKU Linz. He contributes to a variety of ML/DL-related scientific projects for continual learning, semantic segmentation, computer vision, generative modeling, medical applications, and certification in cooperation with companies including AGFA Healthcare, TÜV Austria, and Audi. Moreover, he is experienced in simulating astrodynamical processes such as gravitational n-body systems and plastic-elastic collision processes for planet formation. Since 2022, Philip is working as a Machine Learning researcher in the Biomedical Image Informatics group at VRVis.
Thursday: "From idea to final project"
Stavrina Dimosthenous (University of Manchester), Data/Code Management, reproducibility
Delving into the world of data-driven research presents exciting possibilities. However, there are a few topics that need to be addressed before one can jump right in.
Research data management (RDM) planning, software version control, automation, and data cleaning might appear dry at first glance, and they might indeed be to many. Despite these topics and practices seeming like ‘checkbox’ activities, expending some time actively thinking about them, and setting them up can save a lot of time and set you up for success in your research endeavour.
This workshop aims to introduce you to these topics. By the end of the workshop you will be prepared to independently self-teach these topics.
We will begin by exploring some academic research project examples and how RDM and RDM planning could be approached.
Moving on, I will introduce software version control via Git, with remotes on the developer platform, GitHub, and touching on working as a team on GitHub. This exercise will also explore automation via GitHub Actions and Docker.
We finish with data cleaning and wrangling concepts, and a practical demonstration in Python.
Participation by following along is encouraged but not expected.
Erich Birngruber (ÖAW/CLIP), Introduction to CLIP
Friday: "Explainability"
Gunnar König (University of Tübingen) "Explainability of Neural Networks in STEM fields" Part I
Due to their predictive accuracy, machine learning models are increasingly employed in high-stakes decision making and in scientific contexts. These predictive capabilities often come at the price of interpretability: The models are too complex to be inherently intelligible by their human users. In an attempt to restore this interpretability, a broad range of methods have been developed, often subsumed under the umbrella of the term Explainable AI (XAI). In this session, we will give the attendees an introduction to the field. We will start by mapping the different approaches using the standard taxonomies, before we formally introduce some of the most popular explanation methods. Over the course of the session we will focus on the core challenges that practitioners face: (1) Translating the outputs of XAI methods into concise statements about model and data, and (2) choosing the explanation technique that is most suitable for a given task. We will tackle these questions with a particular focus on the task of learning about feature target associations, thereby preparing attendees to employ XAI methods in their own work.
Moritz Grosse-Wentrup (University of Vienna) "Explainability of Neural Networks in STEM fields" Part II
Machine learning (ML) models are increasingly deployed in high-stakes environments, e.g., in the health domain, where ethical and legal considerations require models to be interpretable. Despite substantial progress in interpretable ML (IML), several key challenges remain. These include distinguishing between interpreting the model and using the model to interpret the data-generating process, dealing with heterogeneous data, and providing meaningful recourse recommendations. I argue that we can address these challenges by adopting a causal perspective on IML. In particular, I demonstrate how the causal structures of the model and the data-generating process jointly affect model interpretation techniques. I then provide an overview of our recent work on leveraging causal techniques to improve model interpretation and render recourse recommendations more meaningful.
Pia Sommerauer (Vrije Universiteit Amsterdam), "Evaluation and Interpretability of NLP systems"
(Large) language models achieve impressive results on various NLP tasks. At the same time, it is difficult to tell to what degree language models can reflect a human-like understanding of semantics and how specific information is reflected. In this session, we will take a critical look at the strengths and weaknesses of (L)LLMs and consider how LLM-based systems can be evaluated. In a practical, hands-on session, we will build a challenge dataset using a behavioral testing approach.
Pia Sommerauer is an assistant professor at VU Amsterdam. Her research focuses on understanding how people use language to form (social) categories and on how language models represent social and semantic categories. She approaches these questions from interdisciplinary perspectives and collaborates with experts in fields such as communication science and philosophy. She teaches courses in programming and Natural Language Processing to diverse and interdisciplinary groups of students.