Navigation auf


Department of Informatics

IfI Summer School 2024

The IfI Summer School is a week-long event for PhD students and research assistants in informatics and related fields, where invited experts teach a number of different topics in day-long courses.

Dates and Location

The IfI Summer School will take place between 24 June - 28 June 2024 at the University of Zurich, Department of Informatics.

Course location:
Binzmühlestrasse 14
8050 Zurich
Class room BIN 2.A.01

List of Courses

Day Course Instructor ECTS credits
24 June

Human-Centered Explainable AI

Prof. Dr. Katrien Verbert 0.5 Doctoral 
25 June
The Art of Creating AI Characters Mariana Lin, MFA, JD 0.5 Doctoral
26 June
Justice through Design

Prof. Sarah Fox, Ph.D.

0.5 Doctoral

27 June

Modern NLP with Large Language Models

Dr. Debjit Paul

0.5 Doctoral
28 June
How to Operate with Rotations and Rigid Body Motions? An Introductory Lie Group Perspective

Prof. Dr. Guillermo Gallego

0.5 Doctoral

Please note: All courses cover a full day. You need to attend the full day to get the 0.5 ECTS credits!

Please make sure your register for each course you want to attend separately.

Daily Schedule

08:45 - 09:00 Check-in
09:00 - 10:15 Instruction
10:15 - 10:45 Coffee break
10:45 - 12:00 Instruction
12:00 - 13:00 Lunch break
13:00 - 15:00 Instruction
15:00 - 15:30 Coffee break
15:30 - 17:00 Instruction

Registration and Fees

The Summer School is primarily targeted towards doctoral students in computer science and related fields from the University of Zurich as well as other universities.

Registration is closed
- The fees can only be paid by credit card, PostFinance or TWINT using the registration links.
- Please make sure your register for each course you want to attend separately.
- Please note that we cannot issue any invitation letters for visa issues.
- Contact: Karin Sigg

- Registration is free for IfI  and CL research assistants, IfI and CL doctoral students, and IfI and CL postdocs
- For all other UZH participants, fees are 50 CHF per course day. 
- For all other participants, fees are 100 CHF per course day. 

ECTS Credits

For UZH students, you can find the ECTS credit awarded by each course in the overview above. Non-IfI students who would like to acquire credits, need to talk with the person who is in charge of credit transferring at their home university first and find out if the ECTS credits awarded by IfI at UZH are accepted/recognized.

Courses and Instructors

MONDAY 24 June

Human-Centered Explainable AI

Course Description

In this one-day course on Human-Centered Explainable AI (HCXAI), I will cover the basics of explainable AI, exploring different explainability methods (global/local, model specific/model agnostic) and examples of these methods in different application domains. The course will also cover various human-computer interaction methods aimed at adapting such explainability methods to the needs of end-users. Additionally, data visualisation principles and techniques will be covered to communicate complex AI insights clearly and intuitively. Hands-on activities include the use of human-computer interaction methods to co-create HCXAI interfaces and to evaluate the usability of such interfaces with end-users. 

Instructor Prof. Dr. Katrien Verbert


Katrien Verbert is professor at the Augment research group of KU Leuven. She obtained a doctoral degree in Computer Science in 2008 at KU Leuven, Belgium. She was a postdoctoral researcher of the Research Foundation – Flanders (FWO) at KU Leuven. She was an Assistant Professor at TU Eindhoven, the Netherlands (2013 –2014) and  Vrije Universiteit Brussel, Belgium (2014 – 2015). Her research interests include visualisation techniques, recommender systems, explainable AI, and visual analytics. She has been involved in several European and Flemish projects on these topics, including the EU ROLE, STELLAR, STELA, ABLE, LALA, PERSFO, Smart Tags and BigDataGrapes projects. She is also involved in the organisation of several conferences and workshops (program chair ACM RecSys 2024, general chair IUI 2021, program chair LAK 2020, general chair EC-TEL 2017, program chair EC-TEL 2016, workshop chair EDM 2015, program chair LAK 2013 and program co-chair of the EdRecSys, VISLA and XLA workshop series, DC chair IUI 2017, DC chair LAK 2019).


The Art of Creating AI Characters

Course Description In every dystopian vision of a singularity in which machines take over the world, AI is depicted as soulless beings stripped of virtue and meaning. In reality, the potential for AI to exist as our delightful compatriots, incarnated to accompany us in this strange and lonely existence, is enormous—and depends only on the humans who design it. It’s this belief that underlies this course, a marriage of theory and practice: we will discuss why creativity in AI character design is critical to the future of human-AI relationships, and explore practical strategies to design AI personae to enhance every application. We will learn about creative choices in purpose, identity, backstory, belief systems, aesthetics, and personal language. In workshop, you will prototype an AI persona for a particular application, and present your character. This course welcomes all who are ready to be playful, and explore the humorous, strange, and magical possibilities for AI.
Instructor Mariana Lin, MFA, JD


Mariana Lin is a writer based in Paris, and former creative director and principal writer behind Apple’s Siri. She has worked in AI character writing since 2014, and since Apple has gone on to develop AI characters for Hanson Robotics’ Sophia, Bose, BMW and Renault. She holds an MFA in poetry from Pacific University, a JD in intellectual property from Berkeley Law School, and a BA in English Literature from Swarthmore College. She has spoken on writing for AI at TED Global Summit, UNESCO, AI for Good at the United Nations, among other global conferences. She has taught on creative writing for AI at Stanford University. Her writing and poetry have appeared in publications such as Prairie Schooner, The Paris Review, and New York Magazine.


Justice through Design

Course Description This course examines histories of professional ethics and activism to offer a set of techniques and orientations for design practice focused on dismantling structural inequality and advancing justice. We will explore how communities have sought to counter harmful designs by creating alternative objects, systems, and organizations. This one-day course will include both lecture and hands-on activities in which students will analyze existing systems, engage ambiguous problems, imagine and propose alternative designs (e.g., artifacts, environments).
Instructor Prof. Sarah Fox, Ph.D.


Sarah Fox is an Assistant Professor at Carnegie Mellon University in the Human Computer Interaction Institute, where she directs the Tech Solidarity Lab. Her work examines the impacts of AI and automation on essential work sectors, with a focus on developing systems that center workers’ needs and expertise. She holds a Ph.D. in Human Centered Design & Engineering from the University of Washington.


Modern NLP with Large Language Models

Course Description In this lecture, we will cover the foundations of modern methods for natural language processing, such as word embeddings, recurrent neural networks, transformers, pretraining, and prompting. We will discuss how these methods can be applied to important tasks in the field, such as language generation, question answering, text classification, etc. The lecture will also cover issues with these state-of-the-art approaches, identify their failure modes in different NLP applications, and discuss analysis and mitigation techniques for these issues. 
Instructor Dr. Debjit Paul


Debjit Paul is a postdoctoral researcher in the School of Computer and Communication Sciences at the École Polytechnique Fédéral de Lausanne (EPFL). He received his PhD in Computational Linguistics from Heidelberg University. His research focuses on natural language reasoning, aligning AI models with human feedback and explainable artificial intelligence (xAI). He has served as an Area Chair at EMNLP 2023 and ACL 2024 and as a committee member of several conferences and workshops (e.g., ACL, EMNLP, NAACL, EACL, etc.). 

FRIDAY 28 June

How to Operate with Rotations and Rigid Body Motions? An Introductory Lie Group Perspective

Course Description Rotations and rigid-body motions describe the continuous location of objects in the world, and they are quite different from the usual vector quantities that we are familiar with. They do not form vector spaces, which means that we cannot simply "add" two rotations. Instead, they constitute the special orthogonal group SO(3) and the special Euclidean group SE(3). In this course we will learn how to work with rotations and rigid-body transformations from the perspective of Lie groups. We will walk through different examples and application scenarios, partially inspired by robotics. The tools studied are having a large impact in modern estimation algorithms.
Instructor Prof. Dr. Guillermo Gallego


Guillermo Gallego is Associate Professor at TU Berlin and the Einstein Center Digital Future, Berlin, Germany. He is also a principal investigator at the Science of Intelligence Excellence Cluster. He received the PhD degree in Electrical and Computer Engineering from the Georgia Institute of Technology, USA, in 2011. From 2011 to 2014 he was a Marie Curie researcher with Universidad Politecnica de Madrid, Spain, and from 2014 to 2019 he was a postdoctoral researcher with the Robotics and Perception Group of Prof. Davide Scaramuzza at the University of Zurich, Switzerland. He serves as Associate Editor for IEEE Transactions on Pattern Analysis and Machine Intelligence, IEEE Robotics and Automation Letters and the International Journal of Robotics Research. Since 2022, he also co-directs the HEBRiDS graduate school in data science in Berlin, Germany.