Seminar in Deep Neural Networks (FS 2026)

Organization

When & Where: Tuesdays 10:15 - 12:00, ETZ E 9.
First seminar: 17.02.2026
Last seminar: 26.05.2026
Easter holidays: No seminar on 07.04.2026
Coordinators: Frédéric Berdoz, Roger Wattenhofer.

Background

This is a seminar, we will focus on recent research and skip most of the basics. We assume that all participants are familiar with the fundamentals on deep neural networks. If you feel like you cannot follow the discussions, please check out this playlist, this lecture, the book by Francois Chollet on Deep Learning with Python, or any other lectures or books on deep neural networks. As a seminar participant, you are asked to attend all the talks and make a presentation.

Seminar Timeline

When you sign up to the seminar on myStudies, you will automatically be placed on a waiting list.
Before the start of the semester, we will publish a list of papers (you will be notified by mail). You can then tell us what your preferences are.
We will assign the papers (and consequently grant a definitive spot in the seminar) on a first-come first-serve principle, based on how quickly you submit these preferences. The presentations will also be scheduled in this order. Further, you will be assigned a mentor that is familiar with the topic and helps you with the preparation of your presentation.
In the first week of the semester, there will be no presentations. Instead, we will give an introduction to the seminar and some tips on scientific presentations.
After that, every week two students will present their respective papers.

Preparation Timeline

Around 4 weeks before your talk: first meeting with your mentor where you discuss the structure of the talk.
4 to 1 week before your talk: you meet with your mentor as often as both parties find necessary to be making progress.
At least 1 week before your talk: The presentation is ready, and you will present your presentation (as a test run) to your mentor only.
Your mentor will get a copy of your test run presentation slides. (These slides will not become public, but they may influence your seminar grade.)
Your mentor will give you feedback, and you are supposed to update your final presentation based on this feedback.
Please send us your slides at least on the day before your presentation.

Your Presentation

Your presentation should be 30 minutes long.
After your presentation, you should organize a lively discussion about your presentation, for up to 15 minutes.
It may help discussions if you also try to be critical about the presented work.
Your presentation should take into account these presentation guidelines.
Beyond these guidelines, you may find other useful tips about good scientific presentations online, for instance here, or here.
All work copy/pasted from others (figures, explanations, examples, or equations) must be properly referenced.

Grade

The most important part of your grade will be the quality of your presentation, both content and style. In addition, we grade how well you direct the discussions with the audience, during and after the presentation. Beside your final presentation, we also grade how actively you participate in the discussions throughout the semester and we value the quality of your mentor-only test presentation. Attendance is mandatory.

Schedule

Date	Presenter	Title	Mentor	Slides
February 17	Frédéric Berdoz	Introduction to Scientific Presentations	-	[pdf]
February 24	Jonathan Maillefaud	Generative Graph Pattern Machine	Saku Peltonen	-
February 24	-	TBA	-	-
March 03	Tom Haidinger	Neural Message-Passing on Attention Graphs for Hallucination Detection	Florian Grötschla	-
March 03	Yucheng Wang	MiMo-Audio: Audio Language Models are Few-Shot Learners	Luca Lanzendörfer	-
March 10	Frederico Aberle	Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?	Frédéric Berdoz	-
March 10	Daven Lim	Do Language Models Use Their Depth Efficiently?	Joël Mathys	-
March 17	Mara Godeanu	SAM Audio: Segment Anything in Audio	Florian Grötschla	-
March 17	Klejdi Sevdari	VOICECRAFT: Zero-Shot Speech Editing and Text-to-Speech in the Wild	Luca Lanzendörfer	-
March 24	Rui Wang	WHALE: Towards Generalizable and Scalable World Models for Embodied Decision-making	David Jenny	-
March 24	Maximilian Schlegel	Extending the Context of Pretrained LLMs by Dropping Their Positional Embeddings	Frédéric Berdoz	-
March 31	Ioana Gabor	The quest for the GRAph Level autoEncoder (GRALE)	Joël Mathys	-
March 31	Peter Jolles	Graph Positional Encoding via Random Feature Propagation	Saku Peltonen	-
April 07	-	Easter break	-	-
April 14	Prathamesh Tagore	Sign and Basis Invariant Networks for Spectral Graph Representation Learning	Saku Peltonen	-
April 14	Sichao Ma	Continuous Audio Language Models	Florian Grötschla	-
April 21	Benedict Armstrong	Energy-Based Transformers are Scalable Learners and Thinkers	Joël Mathys	-
April 21	Felix Quernheim	Generalizable Insights for Graph Transformers in Theory and Practice	Joël Mathys	-
April 28	-	No Seminar	-	-
May 05	Felix Schatzl	DISCOVER: Automated Curricula for Sparse-Reward Reinforcement Learning	David Jenny	-
May 05	-	TBA	-	-
May 12	Federico Lin	Differentiable Euler Characteristic Transforms for Shape Classification	Saku Peltonen	-
May 12	Georgios Sideris	Collaborative Learning in the Jungle	Antonio Di Maio	-
May 19	Baraq Ben-Or Lipshitz	LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics	Andreas Plesner	-
May 19	Samvit Mavinkurve	You Cannot Feed Two Birds with One Score: the Accuracy-Naturalness Tradeoff in Translation	Till Aczel	-
May 26	Lin Che	Overtrained Language Models Are Harder to Fine-Tune	Andreas Plesner	-
May 26	Louis Barinka	What makes an image realistic?	Till Aczel	-