Seminar Assignment Summer 2024

The central registration for all computer science seminars will open on March 12th.

This system is used to distribute students among the available seminars offered by the CS department. To register for any of the seminars, you have to register here until April 17th, 23:59 CET. You can select which seminar you would like to take, and will then be automatically assigned to one of them on April 19th.

Please note the following:

  • We aim to provide a fair mapping that respects your wishes, but at the same time also respects the preferences of your fellow students.
  • Experience has shown that particular seminars are more popular than others, yet these seminars cannot fit all students.
  • Please only select seminars if you are certain that you actually do want to complete a seminar this semester. If you have already obtained sufficient seminar credits, or plan to take other courses this semester, feel free not to choose any seminars. Students who drop out of seminars take away places from those, who might urgently need a space or are strongly interested in the topic.
  • We encourage those students who wish to take a seminar this semester, to select their preferences for all available seminars, which eases the process to assign students that do not fit the overly popular seminars to another, less crowded one. So if you are serious about taking a seminar this semester, please select at least three seminars (with priority from "High" to "Low").
  • If you urgently need to be assigned to a seminar in the upcoming semester, choose at least five seminars (with priority from "High" to "Low"). We will then guarantee that you will be assigned to a seminar (yet not necessarily one of your choice).
  • If you are really dedicated to one particular seminar, and you do not want any other seminar, please select the "No seminar" as second and third positive option. However, this may ultimately lead to the situation that you are not assigned to any seminar. Also, choosing "No seminar" as second/third option does not increase your chances of getting your first choice.

The assignment will be performed by a constraint solver on April 19th, 2024. You will be added to the respective seminars automatically and be notified about this shortly thereafter. Please note that the assignment cannot be optimal for all students if you drop the assigned seminar, i.e., make only serious choices to avoid penalty to others.

Register now! Registration is open! You can apply for these seminars until Wednesday, 17.04.2024 23:59.


A Connectionist’s View on Machine Learning by Rebekka Burkholz

Graph structured data is available in abundance to model the world and reason about it. For instance, social networks, chemical molecules, biological networks, and even deep neural networks rely on nodes that exchange information and interact in nonlinear ways.
How can machine learning algorithms make use of such connections?
In this seminar, we will discuss different ways to leverage graph information, either in form of graph neural networks, graph transformers, or as inspiration of sparse neural network architectures. In doing so, we will face typical challenges like their trainability, implicit biases, over-smoothing, over-squashing, etc., and some potential solutions. Not stopping there, we will also use our insights to study contemporary deep learning challenges from a Connectionist's point of view.

Course organization:
-Kick-off meeting in the first or second week of the semester.
-We will have a block course in the winter break (date and time tbd at kick-off meeting) with one presentation and discussion of a topic per person.
-Note that some (light load of) written deliverables will be due before the block course meeting and a seminar paper one week after the meeting.

More information can be found here:

Requirements: The course has no formal requirements but preference will be given to Master students in Computer Science and related fields with prior knowledge in deep learning and a convincing motivation.

Places: 12

Advanced Rendering Techniques by Alexander Rath, Philipp Slusallek

What does it take to render stunning life-like visuals, like those from your favorite blockbusters? In this seminar, the students jointly decide on a shot they want to re-create, and then build both the virtual 3D scene, as well as the program that will produce a photo-realistic render thereof. Based on the shot, each student is assigned an advanced rendering topic (volume rendering, path guiding, etc) and is then responsible for implementing it in both the scene and the renderer. The work will be supported through close collaboration with expert advisors from our chair, funds for professional 3D assets, compute clusters of the university, and high-end workstations at our chair.

There will be an initial meeting to pick the shot and assign topics at the end of April, and from then on there will be weekly one-hour meetings with short status updates (3 minutes per student) followed by a joint discussion of next steps. Finally, each student will give a final presentation of their work at the end of August. The exact dates are flexible, and will be determined together with the students.

Since this project is a team effort, you will be required to work at a constant pace throughout the semester (plan for a total of 11 hours per week). Working on the scene will happen in-person (on a high-end workstation) at the chair (two 120 minutes slots each week, you get to pick when).

See the seminar website for more information ( or contact me via email ( in case there's any questions!

Requirements: You are required to satisfy these requirements:

- Fascination for computer graphics
- Programming will be done in C++ (basic knowledge is sufficient)
- Experience with path tracers (e.g., Realistic Image Synthesis, CG1 in 2023/2024, or personal projects)
- Basic experience with Blender

Places: 11

Advances in AI for Autonomous Driving (AI4AD) by Matthias Klusch, Andreas Nonnengart, André Meyer-Vitali, Christian Müller

This seminar (AI4AD) is concerned with advances in autonomous driving research from the perspective of AI. In particular, we will take a closer look at selected techniques and systems of (neuro-symbolic) AI for autonomous driving with focus on pedestrian behavior prediction and collision-free navigation, and discuss their strengths and weaknesses. 

Seminar webpage:

The seminar is held on Tuesday from 16:15 - 18:00.

Seminar introduction meeting with topic assignments is on Tuesday, April 23, 2024, 16:15 - 18:00.

The seminar takes place in-person at DFKI Saarbrücken, SIC Bldg. D3.2, room DFKI NB +2.31 "Turing II".

Requirements: Good knowledge in AI (introductory course on AI covering symbolic knowledge representation and reasoning, machine learning, i.p. deep learning, and automated planning) is required.

Places: 11

AI for HCI: Optimization Methods in User Interface Design and Adaptation by Anna Maria Feit, João Belo

The recent advances in AI and other computational methods have changed how we design and create user interfaces. Optimization methods and machine learning techniques can be used to automate parts of the design process, support designers in their creativity, optimize the user experience, and automatically adapt interfaces to a person's context and preferences.
In this seminar, we will learn about specific algorithms and AI methods from optimization and machine learning and see how they are applied to problems in Human-Computer Interaction (HCI). This seminar is highly interactive and builds on the participation of all students. Every week, you will read about an algorithmic method and a paper that applies this method to an HCI problem. Students take turns assuming different roles, acting as presenter, developer, journalist, and more. Thus, you will practice your presentation and writing skills but also get a chance to implement one of the methods yourself. The format is very interactive, and students typically enjoy the lively discussions.
See the seminar page for more details:

The seminar will take place on Mondays, 14 - 16 in E.1.7 R3.23. The kick-off meeting will be on 22nd of April after which we will assign topics.

Requirements: Programming will be done in Python. Please confirm your prior experience with this language or your willingness to spend extra hours to learn it.

Experience with at least one of the following topics is beneficial (please indicate):
- Optimization methods (Integer Programming, Genetic algorithms, Simulated annealing, etc.)
- Deep learning methods (e.g., CNN, RNN, Autoencoder, etc. )
- Bayesian methods (e.g., bayesian inference, bayesian optimization)
- Multi-armed Bandits or other probabilistic methods

Places: 10

Aligning Language Models with Humans: Methods and Challenges by Michael Hahn

We will look into the rapidly developing field of aligning language models with human preferences, a central ingredient in today's LLMs. In the narrow sense, this refers to the finetuning process by which language models , originally trained to predict the next token, are turned into chatbots and other systems that can meaningfully interact with humans. Here, technical ideas such as Reinforcement Learning from Human Feedback are relevant. In a broader sense, this refers to research on how we can ensure LLMs behave in ways that humans desire, e.g. follow social and ethical norms, and are robust to malevolent adversarial prompting.

We will read a diverse set of recent technical papers from this highly dynamic field.

See the course website for more:

If you want to take the course, please email your top-3 preferences among the items in the syllabus, and a brief explanation why you want to take this course and feel prepared for it.

Requirements: Required: Background in machine learning.
Recommended: Background in natural language processing.

Places: 12

Aspects of Quantitative Program Verification by Benjamin Kaminski, Tobias Gürtler

Are you passionate about logic, verification, semantics, and alike? Are you tired of thinking black-and-white, true-or-false? Then come and study the more nuanced quantitative formal program verification! In quantitative verification, properties are not just true or false. Instead, we verify quantities like runtimes, error probabilities, beliefs, etc.

Topics which we will cover include:

- Probabilistic programming (a currently trending modeling paradigm in machine learning),

- The geometry of neural networks

- Incorrectness logic (the latest creation of the former chief formal methods researcher at Facebook)

- The flow of quantitative information through programs

- Worst-case execution times

- Verification of heap-manipulating programs

- and many more

The seminar website can be found here:

Requirements: The most important requirement: You should really really like math and/or logic. This seminar covers very theoretical work.

The following courses are mandatory and/or recommended.

Mandatory: Programmierung 1, Programmierung 2, Grundzüge der Theoretischen Informatik

Recommended: Semantics; Introduction to Computational Logic; Automata, Games and Verification;

Ideal: Verification

Places: 6

Bio-based Fabrication for Sustainable Interactive Systems by Madalina Nicolae, Ata Otaran, Prof. Dr. Jürgen Steimle

In today's rapidly evolving technological landscape, there is a growing awareness of the need for sustainable solutions that minimize environmental impact while still pushing the boundaries of innovation. The seminar aims to address this pressing need by guiding students through the exciting realm of bio-inspired design, interactive technologies, and eco-conscious prototyping. Students will acquire conceptual, technical and practical skills in using bio-based fabrication for fabricating interactive systems.

The seminar offers diverse concrete project themes to work on, each focusing on leveraging biodegradable materials and biomimetic principles to develop interactive systems that not only enhance user experiences but also contribute to a more sustainable future. From biohybrid interfaces and bio-inspired robotics to biofeedback and edible interfaces, students will have the opportunity to learn about innovative concepts at the forefront of human-computer interaction (HCI), biodesign and sustainability. Throughout the seminar, students will be encouraged to think critically about the ethical implications of their designs, considering factors such as environmental impact, accessibility, and ethical implications.

The mandatory plenary sessions will be held on Wednesday, 4 - 6 pm in Building E1.7 . More details about the session dates and topics :

Requirements: Requirements:
- For the registration, we require you to submit a brief motivation statement that elaborates on why you want to take this class and what relevant projects and courses you have taken before.
- It is highly recommended to have passed Interactive Systems and/or HCI.
- This is a Master-level seminar, which can also be taken by Bachelor students from the 5th study semester and above.

Places: 12

Bridging the Gap: Language Models and Structured Knowledge in AI by Gerrit Großmann, Cennet Oguz, Verena Wolf

This is a block seminar in September 2024, which will be held in cooperation between the Department of Multilingual Technologies (MLT) and Neuro-Mechanistic Modeling (NMM).

Large language models (LLMs) have swiftly become a cornerstone in AI research, capturing the attention of the public as the most accessible gateway to artificial intelligence. Despite their groundbreaking impact, LLMs are not without their imperfections. Notably, the occurrence of hallucinations and limited reasoning capabilities, particularly in specialized domains, remain significant challenges.

This seminar begins by investigating the theoretical foundations of language representations, tracing the evolution of transformers and their progression towards the cutting-edge LLMs we see today. Building on this foundation, the seminar will then explore promising future directions. Special emphasis will be placed on the integration of LLMs with neuro-symbolic reasoning and the enrichment of these models through knowledge graphs and other forms of structured data.

Requirements: We expect no prior knowledge in language modeling.
Knowledge of ML will be an advantage.

Places: 8

Classical Concepts of Computer Vision and Computer Graphics in the Neural Age by Christian Theobalt, Marc Habermann, Thomas Leimkühler, Rishabh Dabral

Computer Vision strives to develop algorithms for understanding, interpreting and reconstructing information about real-world scenes from image and video data. Computer Graphics focuses on image synthesis: algorithms to build and edit static and dynamic virtual worlds and to display them in photorealistic or stylized ways. Both fields have witnessed the transformative effects of deep learning and neural networks, thus ushering the so-called Neural Age.

In this seminar, we will explore how the classical concepts in Computer Vision and Computer Graphics have manifested in the Neural Age. We will seek to understand if and how the new neural methods have changed the way we think about these problems, and how they have improved the state-of-the-art. For each topic that we cover, we will discuss a seminal paper that has shaped the field and also discuss a recent paper that has further developed that idea in a modern context. This seminar will cover research papers from the following topics:

- image and video generation, manipulation, and analysis,
- multi-view geometry and reconstruction,
- computational photography and videography,
- shape matching,
- pose estimation, tracking, and character animation,
- deep learning for computer vision and computer graphics.

Seminar webpage:

Requirements: This seminar is aimed at graduate students in computer science or related fields. Successful completion of Computer Graphics 1 and Image Processing and Computer Vision is recommended, but not strictly required.

Places: 12

Compositionality by Kate McCurdy, Michael Hahn

Compositionality --- roughly, the ability to correctly process wholes given the ability to correctly process their parts --- is a core property of human cognition and especially natural language, where it enables ``infinite use of finite means'' as known linguistic elements combine to produce novel words and sentences. Recent advances in Natural Language Processing have raised new questions in this domain: are modern artificial neural networks capable of compositional generalization --- and for that matter, how capable are humans? This blockseminar briefly reviews foundational and recent work on the core scientific question of compositionality.

The course will meet once during the summer semester for an introduction and coordination session, and then in three three-hour sessions over the course of a week in September.

For more information, please review the course page:

Requirements: Required: motivation statement.
Strongly recommended: Background in linguistics and/or natural language processing.

Places: 4

Computer-Assisted Proofs in LEAN by Laurent Bartholdi, Leon Pernak

As mathematical research advances, researchers become more and more specialized, and the mathematics they produce becomes more and more complicated to verify.
The possibility to formalize and check proofs thanks to computer programs is thus more relevant than ever. What’s more, tremendous progress in recent years make it so that formalizing actual research level mathematics is possible, and formalizing student level mathematics is accessible to students.
In this seminar, students will practice with the LEAN proof assistant (
We meet weekly on Zoom, and discuss informally: each student gets a chance to speak, to explain the work they have done in previous weeks, and to plan ahead.
See the course's page to obtain the zoom link.

Requirements: Students may obtain up to 8 credit points, by formalizing a theorem or new definitions, thus contributing to mathlib, the library which gathers all mathematics that has already been formalized in LEAN.
Topics suitable to both MSc and BSc students will be offered, no prior knowledge is required.

Places: 10

Data-driven Understanding of the Disinformation Epidemic (DUDE) by Yang Zhang

Arguably, one of the greatest inventions of humanity is the Web. Despite the fact it revolutionized our lives, the Web has also introduced or amplified a set of several social issues like the spread of disinformation and hateful content to a large number of people.

In this seminar, we will look into research that focuses on extracting insights from large corpus of data with the goal to understand emerging socio-technical issues on the Web such as the dissemination of disinformation and hateful content. We will read, present, and discuss papers that follow a data-driven approach to analyze large-scale datasets across several axes to study the multi-faceted aspects of emerging issues like disinformation.

During this seminar, the participants will have the opportunity to learn about state-of-the-art techniques and tools that are used for large-scale processing, including, but not limited to, statistical techniques, machine learning, image analysis, and natural language processing techniques.

Requirements: There are no formal prerequisites for this seminar. Despite this fact, it will be helpful if the participants have a basic understanding of machine learning.

Places: 20

Design and Development of Interactive Technologies for Teaching Complex Systems by Man Su, Tomohiro Nagashima

Ever wondered why geese fly in a “V” shape, why viruses spread so quickly, or what produces the ripple effect of traffic jams? Ever thought about explaining these everyday complex systems through using interactive visuals or simulations? This course is a collaborative exploration into the design and development of advanced technologies aimed at teaching complex system concepts to students or pupils. Some key components include:
(1) Exploration of Existing Simulations: Introduction to the use of simulations (e.g., agent-based models, machine learning agents) for visualizing and understanding complex systems.
(2) Hands-on experiences: Exploring the potential of embedding interactive simulations into intelligent tutoring systems (e.g., Cognitive Tutoring Authorization Tool) or other immersive learning environments (e.g., VR or AR or virtual games).
(3) Co-Design Project: The class will act as small design groups, co-creating interactive educational tools to teach complex systems.
(4) Research and Reading: Analysis and discussion of papers on the development and application of simulations and other emerging technologies in teaching complex systems, to build a foundational understanding and common goal for the co-design project.

Ideal for Students With:
- Interest or background in computer programming, game design, UX/UI design, graphic design
- Experience or a keen interest in science learning, education technology, and instructional design
- A desire to engage in interdisciplinary collaboration to create educational tools
- A motivation to explore and apply complex system concepts through interactive technologies
- This course promises a unique, interdisciplinary experience, culminating in the creation of an innovative educational tool designed to make complex system concepts accessible and engaging for learners.

Feel free to email for questions!

Requirements: Motivation Statement Requirement:

Applicants are required to submit a motivation statement, outlining their interest in the course and specifying the role (i.e., programmer, designer, instructional designer, product manager, etc.) they wish to undertake within the class project. This statement should reflect the student’s expertise, experience, and how they envision contributing to the co-design of an interactive product to teach complex system concepts.

Places: 8

Embedded Systems Security by Ali Abbasi

From critical infrastructure to consumer electronics, embedded systems are all around us and underpin the technological fabric of everyday life. As a result, the security of embedded systems is crucial to us.

This seminar covers research papers addressing various topics in embedded systems security. This includes topics such as instruction profiling (template attack), fault injection and side-channel attacks, firmware static and dynamic analysis, intrusion detection in embedded systems, automotive/space systems security, and fuzzing embedded systems.

More information is available on the course website:

Requirements: Background in embedded systems security or systems security is a plus.

Places: 8

Explainable Machine Learning (ExML) by Jonas Fischer, Bernt Schiele

In this seminar we will discuss different methodologies in Explainable Machine Learning, which is concerned with understanding what information a Machine Learning system learns and how it uses this information for decision making. We cover both seminal works as well as recent advancements in the field, including post-hoc explainability approaches and inherently interpretable model designs.

The seminar will consistent of an introductory meeting with a lecture at the beginning of the semester introducing the field and distributing papers, and a two-day block course in the semester break covering paper presentations and discussions. Students are expected to read into their assigned paper, the related literature, prepare a talk, as well as a paper summary with critical discussion.


Requirements: The student has a solid understanding of Machine Learning and feels comfortable with Neural Networks (for example through lectures High Level Computer Vision, Neural Networks: Theory and Implementation, or Machine Learning).

Places: 12

GameCraft: Spielmechaniken und Spiele-Prototyping by Dr. Pascal Lessel, Prof. Dr. Maximilian Altmeyer, Prof. Dr. André Miede, Prof. Dr. Antonio Krüger

Diese Veranstaltung ist eine gemeinsame Veranstaltung mit der Hochschule für Technik und Wirtschaft des Saarlandes. Die Veranstaltung findet auf Deutsch statt.

Ziel dieser Veranstaltung ist es, Prototypen zu konzipieren, die nach dem Motto "eine Partie geht noch", Spielende motivieren nach einer Partie, direkt eine neue Partie starten zu wollen. Bei der Konzeption (im Hinblick auf die Implementierungszeit) sind vom Funktionsumfang überschaubare Spiele (wie etwa Tetris) als Vorbild zu nehmen. Dennoch soll das unterliegende Konzept des Prototyps (und damit verbunden die Spielmechanik(en)) innovativ, d. h. nicht nur eine 1:1 Kopie eines existierenden Spieles, sein. Vorlesungsinhalte führen in relevante Themengebiete ein.

Termin: Mittwochs, 14:15 – 15:45, ab 24.04.2024.

Abschlussveranstaltung am 28.08.2024 (bitte nur eine Priorität vergeben, wenn Sie auch an diesem Termin anwesend sein können).

Für mehr Informationen siehe:

Requirements: Sie sollten sich selbst als Konsument von Spielen sehen (egal ob analog oder digital) und das Gefühl haben, ein Gespür für gute Spielemechaniken zu haben.

Der Prototyp soll aus dem Browser heraus spielbar sein. Solange Sie allgemeine Programmierkenntnisse vorweisen können, ist es nicht erforderlich das Sie Webprogrammierkenntnisse haben. Wir stellen entsprechende "Skeletons" bereit, die Sie erweitern können.

Places: 8

Generative AI for Education by Adish Singla

The course will provide an overview of state-of-the-art research on leveraging generative AI to enhance education. We will cover research papers and topics based on a recent NeurIPS’23 workshop we organized (workshop link: The course consists of three main components as follows:

(1) Research papers: During the first half of the semester, students will be assigned up to six research papers and have to write a short report for each paper. These reports will be due during the semester, about one report per week.

(2) Project: During the second half of the semester, students will work on a project.

(3) Final presentation: At the end of the semester, students will give a 25-minute presentation on one of the papers and the project.

There will be no weekly classes. We will schedule regular office hours where students can receive feedback on their reports or projects.

Requirements: There are no formal requirements; however, please note the following points:

(1) Preference will be given to students who have already taken courses covering topics such as human-computer interaction, natural language processing, educational technologies, software engineering, program analysis, artificial intelligence, and machine learning.

(2) We are requesting you to provide a short motivation letter explaining the reasons why you are interested in taking this seminar. In this motivation letter, you can also mention any relevant project(s) you have done and any relevant courses you have taken along with grades obtained. Please provide this information in the text box below.

Places: 15

Groundbreaking Models in Image Analysis by Joachim Weickert

Image processing and computer vision have benefitted from a number of key ideas that have fertilised the subsequent develepment enormously. The goal of this seminar is to study a number of publications that have played a fundamental role in this context and that are cited very often.

Topics include scale-spaces, regularisation, denoising, segmentation, optic flow, stereo, registration, and shape from shading.

The kickoff meeting will take place in the second week of the semester at 16:15 online via Zoom.

The weekly meetings will take place on Tuesday, 16:15 - 18:00, online via Zoom.

For further information, please visit .

Requirements: The seminar is for advanced bachelor or master students in Visual Computing, Mathematics or Computer Science. Basic mathematical knowledge (e.g. Mathematik für Informatiker I-III) is required, and some knowledge in image analysis is recommended.

All papers are written in English, and English is the language of presentation.

Places: 14

How to build a social computer? by Antonio Krüger, Patrick Gebhard, Dimitra Tsovaltzi, Fabrizio Nunnari, Mina Ameli, Chirag Bhuvaneshwara

Computers, mobile phones, and wearables have become an integral part of our daily lives. The user interfaces are designed to interact with factual information, such as health parameters and contextual data. This level of interaction may be adequate for certain applications. However, what if a computer system could understand users like humans do and adapt to their individual social situations to establish a social, human-like interaction? The focus is on social training systems, such as virtual job interview training and work-life balance systems.

This interdisciplinary seminar in Psychology and Artificial Intelligence explores the question of how to make computers social. It examines the concepts and theories that define being social, as well as how humans communicate socially. The seminar also investigates how these concepts can be transferred into computer models and what is technically feasible. This study will present relevant concepts and theories, which will be discussed and applied to computer models. As proof of concept, three interactive social computer applications will be created. The project will involve collaboration between students of Psychology and Computer Science, who will design, implement, and evaluate each application.

See previous seminars:

Requirements: Psychology students should have knowledge in the areas of models of emotions, models of social interaction and requirements. A bachelor degree in Psychology seems appropriate.

Computer Science students should have knowledge in the areas of AI, HCI, and software design. A bachelor degree in Computer Science (or equal) seems appropriate.

The main language is German, English is possible. Why? The seminar is about emotions and values that have to be discussed between psychology and computer science students. Our recommendation is that the seminar language is in German. If students agree that English is used, they should be aware that this will demand for additional efforts (e.g., in-deep explanations).

During the seminar, progress is reported at a specific web page for each project so every seminar participant can get an overview on the activities.

Project slides and short progress reports are in English!

Places: 9

Interactive Prototypes for the Retail of the Future by Antonio Krüger, Frederic Kerber, Felix Kosmalla, André Zenner

In this seminar, we will explore how artificial intelligence (AI) and interactive technologies in the area of Human-Computer-Interaction (HCI) can augment offline shopping experiences in retail stores. During the course of the summer semester you will develop a concept and implement a working prototype that can be showcased to potential users (potential customers as well as employees/management of a retail store).

For further details, please visit the web site:

Requirements: Lectures Programming 2 and Interactive Systems passed.

Places: 12

Language Models at the Intersection of Cognitive Science and Software Engineering by Prof. Dr. Sven Apel

Although tools such as GitHub Copilot provide significant assistance for specific stages of the software development lifecycle, they fall short in supporting other crucial areas. One notable example is the design process, which encompasses tasks such as the creation and refinement of software models, including UML class and sequence diagrams.
This seminar will investigate why this gap exists. A brief review of previous strategies, specifically non-machine learning approaches, will provide an understanding of ongoing challenges in the field and how these can be addressed using large language models.
We will explore the current applications of large language models in automating and assisting the development of software systems. Our objective is to examine the opportunities recent advancements in the machine learning domain (for example, ChatGPT) have unlocked in various areas, such as software model completion.
By also focusing on psychological aspects of software engineering, we aim to understand how contributions not only advance technical capabilities but also support the human elements of software development.

The seminar includes analyzing the contributions of selected papers on code generation, code comprehension, documentation, and model completion as well as discussing potential future directions together.

More information:
The seminar takes place Thursdays from 12:00 -14:00 (4-5 appointments in sum)

Requirements: This seminar is open to Bachelor and Master students. Ideally, students should have already taken courses in Machine Learning, Deep Learning and Software Engineering. But this is not required.
Some foundational knowledge acquired through courses such as Programming 2, the Software Engineering Lab, or similar, would be beneficial.

Places: 9

Machine Learning Approaches to Optimization (Learning to Optimize) by Peter Ochs

The recently growing field of Learning to optimize (L2O) leverages machine learning techniques to develop optimization methods and shares close relations to Meta-Learning. While classic optimization algorithms are hand-crafted and proved to work for certain classes of problems, L2O automates the design based on a (training) data set of typical problems. L2O approaches are data-driven and are therefore tailored to a specific distribution of problems. On one hand, this is achieved by exploiting statistical features and unlocks solution strategies that outperform classical optimization algorithms by several orders of magnitude, however, on the other hand, usually there is no or little theoretical guarantees on the actual performance for a new problem. Generalization bounds like in Empirical Risk Minimization or Statistical Learning in general can be employed to provide some evidence for in-distribution problems. However, typically such an approach is prone to fail for out-of-distribution problems. Therefore, the worlds of L2O and classical optimization must be brought closed together to achieve reliability and speed at the same time. In this seminar, we explore some important research attempts in the world of L2O.

Time slot: Tuesdays 2 - 4 pm.

See for more details.

Requirements: - basics of mathematics (e.g. MFI 1-3)
- basic background in optimization (e.g. from the course "Convex Analysis and Optimization" or "Continuous Optimization"; can be attended in parallel)
- basics of Machine Learning are recommended but not required (we will provide some references)

Places: 12

Machine Learning for Emotion Recognition by Philipp Müller, Chirag Bhuvaneshwara, Benedikt Emanuel Wirth, Mina Ameli, Antonio Krüger

For machines to interact with humans in a natural way, they need to understand the emotional state of humans. Recognizing emotional states is challenging due to the large variability and often subtle nature of emotion expressions. The focus of this seminar is on improving the performance of emotion recognition approaches with modern machine learning algorithms. Students will work in small teams on well-defined practical projects in the field of emotion recognition. The possible projects include video-based emotion recognition from people’s body movements, speech, as well as from Electroencephalography (EEG) recordings. The seminar will allow students to get hands-on experience in applied machine learning.

After three initial meetings in the full group, each team will be closely supervised by the seminar organisers. The deliverables include intermediate and end-of-term presentations, as well as a concise written report.

Seminar website:

Requirements: - The seminar is targeted at master students interested in pursuing research in the social signal processing and affective computing domains
- Theoretical and practical knowledge in machine learning, especially deep learning
- Practical experience with scientific computing in Python

Places: 12

Mining Input Structures by Rafael Dutra + Andreas Zeller

How can one determine the input language of a program to test and debug it thoroughly? In this advanced seminar, we study several approaches to mining input structures and implement them all. Our set of techniques includes:

* Mining Input Grammars
* Learning Tokens
* Learning Input Properties
* Explaining Failures

and more!

The general process will be as follows: Each week, you get 1-2 reading assignments and write an abstract about them. We may also ask you to give an (ungraded) five-minute short presentation to kick off the discussion and improve your presentation skills. Having discussed the approach, you have another week to finish a programming assignment (using Python and Jupyter Notebooks). in which you implement the respective technique in and for Python.

At the end of the seminar, you give a 15-20 minute presentation on one of the techniques, including experiments you designed and conducted. We will determine your final grade from your abstracts (10%), your programming assignments (30%), and the final presentation (60%).

For details, see the course page at

Requirements: This seminar requires creativity and ambition. Experience with formal languages and program analysis is a plus. Prior knowledge in automated testing, debugging, and software engineering (notably from earlier courses) will be beneficial. In your motivation, please mention relevant projects and courses you have taken along with your grades.

Places: 10

Neural Networks in Brains and Computers by Michael Hahn

We will look into the relations between machine learning and neuroscience.

The main target audience is students with a background in computer science who are interested in learning about the brain and how it processes information, how artificial neural networks relate to real neurons, how machine learning can help understand the brain better, and how machine learning models may end up aligning with representations found in the brain.

We will look into questions such as:

- how and why do representations of language models align with brain imaging data of people comprehending language?

- how can we use machine learning for mindreading: decoding thoughts and language from people's brain recordings, even when they aren't talking?

- how do ConvNets and other computer vision architectures relate to the way the brain processes visual information?

- how do both AI and natural intelligence use reinforcement learning to optimize behavior?

and several more.

It is sufficient if you have prior knowledge of either machine learning or neuroscience. However, you should be willing to learn a bit about the other field in preparation for your presentation.

See the course website for more:

If you want to take the course, please email your top-3 preferences among the items in the syllabus.

Requirements: Background in machine learning or neuroscience (one is sufficient).
Knowledge of calculus and linear algebra.

Places: 12

Neural-Symbolic Computing by Matthias Cosler and Bernd Finkbeiner

The way our brain forms thoughts can be classified into two categories (according to Kahneman in his book “Thinking Fast and Slow”):

System 1: fast, automatic, frequent, stereotypic, unconscious. Is this a cat or a dog? What does this sentence mean in English?

System 2: slow, effortful, logical, conscious. 17*16 = ? If a -> b does b -> a?

The traditional view is that deep learning is limited to System 1 type of reasoning. Mostly because of the perception that deep neural networks are unable to solve complex logical reasoning tasks reliably. Historically, applications of machine learning were thus often restricted to sub-problems within larger logical frameworks, such as resolving heuristics in solvers. In this seminar, we will explore new research that shows that deep neural networks are, in fact, able to reason on “symbolic systems”, i.e., systems that are built with symbols like programming languages or formal logics.

Example Topics: What are your chances against an AI in a programming competition? Is it possible to teach temporal logics to neural networks? Can neural networks learn the intuition of mathematicians to improve automated theorem proving?

The seminar takes place on Tuesdays from 16:00 -17:30

See the course website for more:

Requirements: Participants should have strong interest in logical reasoning and/or machine learning. There is, however, no formal prerequisite.

Places: 12

Opportunities and Risks of Large Language Models and Foundation Model by Mario Fritz

The advent of Large Language Models (e.g. ChatGPT) and other foundation models (e.g. stable diffusion) has and will contintue to change the way to AI/ML applications are developed and deployed.

On the one hand, these models show unprecedented performance and can often be adapted to new tasks with little effort. In particular, large language models like ChatGPT have the potential to change the way we implement and deploy functionality.

On the other hand, these models raise several questions related to safety, security and general aspects of trustworthiness, that urgently need to be address to comply with ou high expectations on future AI systems.

Therefore, this seminar will investigate aspects of trustworthiness, security, safety, privacy, robustness, intellectual property.

This is a lecture in the context of the ELSA - European Lighthouse on Secure and Safe AI:

Requirements: Knowledge in AI/ML, NLP

Places: 14

Probing and Analyzing Neural Language Models by Xinting Huang, Michael Hahn

Despite their huge success, neural networks are still widely considered “black-boxes”. In this seminar, we will look into interpretability methods that aim to demystify these models. We will focus on post-hoc interpretability for transformer-based language models, and work on relatively young and burgeoning fields such as Mechanistic Interpretability, which focuses on reverse-engineering model components into human-understandable algorithms. We will read recent papers that involve a diverse set of techniques for interpreting the inner-workings of language models.

See the course website for more:

If you register for the course, you may be directly admitted or waitlisted. Final decisions will be made by the end of the first week of Summer semester.

Requirements: Required: Background in machine learning.
Recommended: Background in natural language processing.

Places: 10

Selected Topics in Mobile Security by Sven Bugiel

In this seminar, we will discuss current results and new problems in the mobile security domain based on relevant scientific papers. The focus of the selected papers lies on Android, given its high popularity among researchers. The topics include usability aspects of Android's permission system and security-relevant APIs, security extensions at different levels of Android's software stack, app analysis, and newly identified attack vectors.

Requirements: Ideally, the participant passed the Adv. Lecture Mobile Security. At least the participant should be familiar with basic security and privacy concepts (e.g., attended the Core Lecture Security or Foundations of Cybersecurity)

Places: 10

Seminar Privacy Engineering und Recht by Prof. Dr. Sorge

Das Seminar „Privacy Engineering und Recht” ist ein interdisziplinäres Seminar für Informatiker und Juristen.

Die Veranstaltung wird dieses Jahr hybrid angeboten.

Ablauf des Seminars

Studierende erhalten während der Vorbesprechung ein Thema und müssen eine Seminararbeit hierzu anfertigen. Innerhalb des gewählten Themas sind die Studierenden in der Schwerpunktsetzung grundsätzlich frei.

Vor der Abgabe der fertigen Seminararbeit ist die Einreichung eines Abstracts nebst einer vorläufigen Gliederung vorgeschrieben. Die Besprechung der Abstracts findet verpflichtend statt, um inhaltlichen Missverständnissen entgegenzuwirken und den Studierenden bereits ein Feedback durch die Betreuer zu ermöglichen.

Danach ist die Abgabe eines „Preprints“ der Seminararbeit erforderlich. Daraufhin findet ein Peer Review der abgegebenen Preprints durch die weiteren Teilnehmer des Seminars statt. Jedem Studierenden werden hierfür 3-4 Paper anderer Studierender zugeteilt, welche von ihm/ihr begutachtet werden. Schließlich finden – in der Regel kurz vor Ende der Vorlesungszeit – die Vorträge statt. Abschließend werden die fertigen Seminararbeiten abgegeben.

Allgemeines: Es gilt der Grundsatz „Tiefe vor Breite“. In der Regel werden breit formulierte Seminarthemen gestellt. Teil Ihrer Aufgabe ist es, selbständig die Literatur zu sichten, sich einen Überblick über das Thema zu verschaffen und sodann einen Schwerpunkt (oder ggf. auch zwei, falls es sich im Einzelfall anbietet) zu setzen. Sie sollen zeigen, dass Sie sich in ein Forschungsthema aus Ihrem Fachgebiet einarbeiten und Sachverhalte aus diesem Forschungsthema vollständig durchdringen können. Das zwingt Sie, viele ebenfalls interessante, angrenzende Aspekte wegzulassen. Ein wesentlicher Teil der Schwierigkeit der Aufgabe ist die Entscheidung, was Sie weglassen können (oder müssen) und welche Aspekte für das Verständnis Ihres Themas wesentlich sind.

In der Einleitung geben Sie eine Motivation und ordnen ihr Thema ein; ggf. bietet sich ein weiterer Abschnitt zu verwandten Arbeiten an, um den Stand der Forschung darzustellen. Dann sollten Sie aber in die Tiefe des von Ihnen gewählten Schwerpunkts gehen. Den Abschluss bildet ein kurzes Fazit.

Abstract: Einarbeitung in das Themengebiet, Literaturrecherche und Studium erster wissenschaftlicher Veröffentlichungen. Auf dieser Grundlage Konkretisierung des gewählten Themas bzw. Wahl des Schwerpunkts innerhalb des Themas sowie die Entscheidung über einen sinnvollen Aufbau. Das Abstract ist eine kurze und aussagekräftige Beschreibung des konkretisierten Themas auf mindestens einer Seite (aber nicht mehr als 1,5 Seiten). Eine erste Gliederung sollte mit dem Abstract eingereicht werden.

Preprint: „Vorversion“ der Seminararbeit, wobei der aktuelle Stand ersichtlich sein muss. Hierbei muss es sich um keine bereits vollumfänglich fertige Arbeit handeln, jedoch muss der Inhalt und das Ziel der Arbeit sowie die Auseinandersetzung mit der einschlägigen Literatur erkennbar sein. Literaturverzeichnis, Gliederung und Schwerpunkt sind notwendige Bestandteile.

(Peer) Review: Feedback, welches sich inhaltlich auf das gesamte Paper erstrecken muss (Quellen, Aufbau/Gliederung, inhaltliche Nachvollziehbarkeit, klare Schwerpunktsetzung sprachliche/grammatikalische Schwächen etc.). Dieses muss aus mind. 400 Zeichen bestehen und soll die Möglichkeit einer ersten Einschätzung der Arbeit geben. Unschädlich ist, dass Juristen Themen der Informatik oder umgekehrt bewerten.

Vortrag: 20 Minuten mit anschließender Diskussion (30 Minuten bei Vorträgen von Zweier-Teams). Die Vorträge sollten sich an ein Publikum aus dem eigenen Fach (also Informatik bzw. Jura) richten, aber ohne spezielle Kenntnisse im Thema des Seminars verständlich sein. Idealerweise sind die Vorträge so gestaltet, dass Fachfremde (also z.B. Juristen bei Informatikvorträgen) die grundlegende Problemstellung erfassen können; eine Verständlichkeit des ganzen Vortrags für Fachfremde ist aber nicht erwartet.

Die Gesamtnote ergibt sich aus dem Preprint, den verfassten Reviews zu den Ausarbeitungen der anderen Studierenden, dem Vortrag und der finalen Seminararbeit.

Die Nichtabgabe des Abstracts, des Preprints, der Reviews oder der finalen Seminararbeit sowie ein Nichterscheinen zum Vortragstermin bzw. den Vortragsterminen führt zum Nichtbestehen des Seminars.

Vorbesprechung: Dienstag, 23.04.2024 / 18-19:30 Uhr

Abgabe Abstracts: 12.05.2024

Besprechungen der Abstracts: Dienstag, 14.05.2024: 09:30 – 12:30 Uhr + 17:00 18:30 Uhr und Donnerstag, 16.05.2024: 15:00 – 18:00 Uhr

Abgabe Preprint: 16.06.204

Abgabe Reviews: 30.06.2024

Vorträge (Anwesenheit an beiden Tagen wird vorausgesetzt): Montag, 15.07. und Dienstag, 16.07.2024

Finale Abgabe der Seminararbeiten: 28.07.2024

Requirements: Es wird erwartet, dass die Teilnehmer in der Lage sind, Vorträgen in deutscher Sprache zu folgen und Ausarbeitungen in deutscher Sprache im Rahmen des Peer Reviews zu lesen (eigene Vorträge und Ausarbeitungen können aber in deutscher oder englischer Sprache angefertigt werden).

Places: 7

Special Topics in Deep Reinforcement Learning by Timo P. Gros, Verena Wolf

Reinforcement learning is a popular technique to solve decision-making problems. In combination with artificial neural networks, it has achieved huge successes in challenging domains such as mastering Atari Games, Chess, or GO.

In this seminar, the participants will learn the theory and practice of the most important concepts of deep reinforcement learning (DRL) and details of popular DRL algorithms. Moreover, it will cover special topics such as safe and causal deep reinforcement learning.

The participants will give presentations and also implement some of these algorithms in small teams to solve the ProgGrid Traffic Gym (PGTG) benchmark. The practical project has been highly appreciated in earlier editions of the seminar.

The kick-off will take place Tuesday, April 23, 2.00 pm.

Requirements: Only participants who successfully participated in the lecture 'Reinforcement Learning' may apply.

Places: 10

The Web Security Seminar by Aurore Fass, Giancarlo Pellegrino, Cristian-Alexandru Staicu, Ben Stock

The Web Security Seminar will teach students to present, analyze, discuss, and summarize papers in different areas of Web security. The seminar combines a reading group with (almost) weekly meetings and a regular seminar, where students will write a seminar paper.

Each student will get a topic assigned, consisting of a lead and a follow-up paper. The student will present the follow-up paper in a 20-minute presentation followed by a 10-minute Q&A. Afterwards we will all discuss the lead paper as a reading group. All students must read the lead paper and, before each session, must submit a summary with strengths and weaknesses.

Finally, each student will write a seminar paper on the topic assigned to them, for which the two papers serve as the starting point.

The seminar slot takes place on Mondays from 12:15 to 14:00.


Places: 10

Topics in Adversarial Machine Learning by Xiao Zhang

This hybrid seminar/proseminar course focuses on understanding the security threats adversaries pose to machine learning systems and the recent algorithmic advancements in building more robust machine learning systems to mitigate those threats. We will particularly focus on theoretical works in adversarial machine learning.

Students will take turns leading discussions on adversarial machine learning topics assigned in advance (including a 45-min presentation plus a 30-min Q&A session). Each student will present twice throughout the semester.

Detailed information is available on CMS:

Weekly attendance in the seminar/proseminar meetings is mandatory.

Requirements: Previous background in statistics and machine learning would be beneficial but optional as long as you are motivated and able to learn relevant fundamentals.

Places: 10

Topics in Computational Social Choice Theory by Kurt Mehlhorn, Nidhi Rathi, Hannaneh Akrami

Human beings live in a social construct that necessarily requires making many group-decisions based on possibly varied preferences/opinions of multiple individuals. The area of computational social choice theory explores designing and analysing methods for such collective decision making. It is a dynamic interdisciplinary field of study at the interface of mathematics, computer science and economics.

In this seminar course, we will learn about the theory of Fair Division which forms an important area of social choice. This area explores the fundamental question of dividing a set of resources among participating agents in a ‘fair’ manner. Along the way, we will also learn about some useful notions from game theory (like Nash equilibrium) and discrete mathematics (like Fixed-point theorems and Sperner's Lemma). Additionally, we will also peek into the world of Matchings via studying the famous ‘Stable Marriage Problem’.

Some initial lectures will be taken by the instructors to explain the basics that will help students to select their paper/topic. The seminar is open for all interested students and postdocs. Students aiming to get credit points must give a regular talk and write a short summary about the paper. The presentation needs to be discussed with us at least one week before your scheduled talk.

See the seminar website for more information ( or contact us (, in case there are any questions!

Requirements: This is a theoretical seminar that will require mathematical maturity (in particular, the ability to understand and write formal mathematical proofs) and a good background in algorithms. A proper preparation of your talk will require non-trivial effort. The target audience of this seminar are master students, PhD students, as well as postdocs.

Places: 10

Trusted AI Planning by Jörg Hoffmann

AI Planning addresses mechanisms taking action decisions in complex environments. More and more this is being addressed by machine learning, in particular neural networks. This raises the issue of trust in what a neural network (or other ML model) has learned. This seminar covers different methods for supporting such trust, encompassing methods for verification, testing, explanation, and re-training. Trusted AI Planning is an emerging field and the entire seminar focuses on recent works in the FAI group.

Requirements: Successful participation in the AI core course, or the AI Planning specialized course is mandatory. Additional experiences in ML are an advantage, but are not required.

Places: 12

Trustworthiness of Foundation Models by Goran Radanovic, Adish Singla

The course will provide an overview of state-of-the-art research on the trustworthiness of foundation models. The course material will comprise research papers covering three different perspectives: (a) red teaming and adversarial testing, focusing on the security aspects of foundation models, (b) fake content generation and watermarking, focusing on content authenticity, and (c) poisoning attacks and robust training, focusing on training-time robustness considerations. This course will familiarize participants with cutting-edge methods employed to assess or enhance the trustworthiness of foundation models.

The students will be asked to write reports on the papers assigned to them and present one of these papers. This course will additionally offer students hands-on experience with foundation models within the context of the topics discussed.

The link to the course webpage is:

Requirements: There are no specific course prerequisites; however, please note the following points:

(1) It would be beneficial for students to have some background in topics such as artificial intelligence, natural language processing, or software engineering.

(2) We are requesting you to provide a short motivation letter explaining the reasons why you are interested in taking this seminar. Please mention any relevant project(s) you have done or relevant course(s) you have taken. You can provide this information in the text box below.

Places: 15

User-Centered Research by Tomohiro Nagashima

Interested in a career as a UX Researcher? Know the basics of HCI but want to get more practical skills and hands-on exercises? Want to conduct an interview study but not sure where to start? Then this seminar may be for you!

In this seminar, we will go through the details of how to conduct user-centered research through several hands-on practical opportunities with iterative rounds of feedback. The goal of this seminar is to help you independently conduct user research on technological products and/or prototypes (a practical goal is to help you apply for (Qualitative) UX Researcher intern/full-time roles in the industry).

In a small-sized casual learning environment, you will get to learn how to set your research question, how to create a consent form, how to obtain user consent, how to prepare a research protocol and interview guide, and how to conduct user research (e.g., interviews, contextual inquiry, think aloud, personas, empathy mapping) in ethical and effective ways. We will also learn how to analyze qualitative data through a couple of analytical techniques that are used in research and industry settings. We would read some papers, and there would be practical activities/assignments for students to experience/apply methods.

Please visit this website for more details (after Mar 13):
Feel free to email for questions!

This seminar is ideal for...

- Students who have taken the HCI lecture but want to get more hands-on experiences and feedback on user research
- Students who are planning to conduct user studies or usability studies for their thesis project
- Students who are interested in a career in UX Research

Requirements: Your interest in learning how to conduct UX research. Prior experience in HCI would be helpful, but not required. There will be some overlapping content with the HCI lecture, but the seminar will focus on the specific area with depth.

In your motivation letter/message, please describe 1) why you are interested in taking this seminar, 2) what relevant project/work/learning experiences you have. 3) Also, if you are planning to conduct user research for your thesis or other projects, please briefly describe it.

Places: 7

Volumetric Imaging & Video: From Pixels to Froxels by Robin Kremer & Thorsten Herfet

The representation of (captured) images and video has remained unchanged since it's infancy: Images are represented as pixels per line and lines per image, videos simply are a series of images. But we've entered an era of severe changes in capturing content: Multicamera-arrays even in mobile devices, depth sensing via Time of Flight or Gated Imaging, volumetric capture via LIDAR and new capture paradigms like event-cameras show, that computational imaging significantly differs from classical film-based capture and hence new forms of representing images and videos are needed.

The seminar will review a palette of approaches for representing volumetric content. From multiview video plus depth (MVD) over point clouds and voxels we will introduce and discuss neural representations like neural radiance fields and neural surfaces as well as volumetric representations that consider the capture setup (Froxels) and we'll compare them to representations like point clouds or voxels.

Requirements: It's advantageous but not strictly required to have passed basic courses on Image Processing and/or Computer Graphic. You should be ready to read and review three scientific papers.

Places: 10

Wireless Security by Mridula Singh

We are surrounded by wireless systems to share confidential information, access bank accounts, report heart rate, etc., incentivizing attackers to eavesdrop and manipulate wireless communication. In this seminar, we will discuss the security, privacy, and availability aspect of wireless systems we use today.

During the first half of the semester, each student will read 5-6 research papers. In the second half, students will work on projects in a team of 2 students. We will meet weekly to discuss the papers and progress of projects. Finally, students will give a 25 min presentation at the end of the semester.

Requirements: There is no formal course requirement for this seminar. Knowledge of signal processing and embedded systems would be useful.

Places: 10