Zurich Pre-ICML 2025 Poster Session

This poster session is a great opportunity to showcase your research and connect with fellow researchers. Not only will we primarily feature posters of papers accepted to this year’s International Conference on Machine Learning (ICML) 2025, but we also welcome recently peer-reviewed work from other conferences, workshops, and journals, as much as space allows.

Register as an attendee or poster presenter: external page https://forms.gle/z7zvnpBkhGQhoEKQ6

Event Details:

• 🎪 What: Pre-ICML 2025 Poster Session
• 👥 Who: academic community (students, scientific staff, industry researchers, professors, ...)
• 🗓️ When: Thursday, June 26, 2025, from 17:00 to 19:30
• 📍Location: ETH AI Center, Andreasstrasse 5, 8092 Zürich – OAT X 11 (Floor 19) external page https://maps.app.goo.gl/ToZTBkCorbE638tE8
• 🆕 Stay up to date about changes by registering as attendee or presenter below

Food, snacks, and beverages will be provided at the event, for those registered.

We look forward to seeing you there!

Confirmed posters

1. external page Prices, Bids, Values: One ML-Powered Combinatorial Auction to Rule Them All
   Ermis Soumalias, Jakob Heiss, Jakob Weissteiner, Sven Seuken
   
2. external page Learning Safety Constraints for Large Language Models
   Xin Chen, Yarden As, Andreas Krause
   
3. external page The underlying structures of self-attention: symmetry, directionality, and emergent dynamics in Transformer training
   Matteo Saponati, Pascal Sager, Pau Vilimelis Aceituno, Thilo Stadelmann, Benjamin Grewe
   
4. external page Prices, Bids, Values: One ML-Powered Combinatorial Auction to Rule Them Al
   Ermis Soumalias, Jakob Heiss, Jakob Weissteiner, and Sven Seuken
5. external page SEEPHYS: Does Seeing Help Thinking? – Benchmarking Vision-Based Physics Reasoning
   Kun Xiang∗, Heng Li∗, Terry Jingchen Zhang∗, Yinya Huang∗,Zirong Liu, Peixin Qu, Jixi He, Jiaqi Chen, Yu-Jie Yuan, Jianhua Han,Hang Xu, Hanhui Li, Mrinmaya Sachan, Xiaodan Liang
6. external page Mind the Gap: Removing the Discretization Gap in Differentiable Logic Gate Networks
   Shakir Yousefi, Andreas Plesner, Till Aczel, Roger Wattenhofer
7. external page Representation Learning for Distributional Perturbation Extrapolation
   Julius von Kügelgen, Jakob Ketterer, Xinwei Shen, Nicolai Meinshausen, Jonas Peters.
8. Continual Benchmarking of LLM-Based Systems on Networking Operations
   Ioannis Protogeros, Laurent Vanbever