The 42nd International Conference on Machine Learning (ICML) will take place in Vancouver, Canada, from July 13 to 19, 2025.
This premier global event unites leading experts focused on advancing machine learning, a pivotal area within artificial intelligence.
ICML is renowned for showcasing and publishing innovative research that spans all facets of machine learning, intersecting closely with fields such as artificial intelligence, statistics, and data science. It also highlights key applications including computer vision, computational biology, speech processing, and robotics.
At ICML 2025, the ELLIS Institute Tübingen will showcase innovative research findings, highlighting its commitment to driving progress in machine learning.
Below is the list of contributions from the ELLIS Institute Tübingen Principal Investigators and Project Leaders (highlighted in bold).
| Title | List of Authors |
|---|---|
| Learning Joint Interventional Effects from Single-Variable Interventions in Additive Models | Armin Kekić, Sergio Garrido Mejia, Bernhard Schölkopf |
| Generative Intervention Models for Causal Perturbation Modeling | Nora Schneider, Lars Lorch, Niki Kilbertus, Bernhard Schölkopf, Andreas Krause |
| Generalized Interpolating Discrete Diffusion | Dimitri von Rütte, Janis Fluri, Yuhui Ding, Antonio Orvieto, Bernhard Schölkopf, Thomas Hofmann |
| LLMs on the Line: Data Determines Loss-to-Loss Scaling Laws | Prasanna Mayilvahanan, Thaddäus Wiedemer, Sayak Mallick, Matthias Bethge, Wieland Brendel |
| LAION-C: An Out-of-Distribution Benchmark for Web-Scale Vision Models | Fanfei Li, Thomas Klein, Wieland Brendel, Robert Geirhos, Roland S. Zimmermann |
| Position: An Empirically Grounded Identifiability Theory Will Accelerate Self Supervised Learning Research | Patrik Reizinger, Randall Balestriero, David Klindt, Wieland Brendel |
| When, Where and Why to Average Weights? | Niccolò Ajroldi, Antonio Orvieto, Jonas Geiping |
| An Interpretable N-gram Perplexity Threat Model for Large Language Model Jailbreaks | Valentyn Boreiko, Alexander Panfilov, Václav Voráček, Matthias Hein, Jonas Geiping |
| Great Language Models Think Alike and this Undermines AI Oversight | Shashwat Goel, Joschka Strüber, Ilze Amanda Auzina, Karuna Chandra, Ponnurangam Kumaraguru, Douwe Kiela, Ameya Pandurang Prabhu, Matthias Bethge, Jonas Geiping |
| Bayesian Neural Scaling Laws Extrapolation with Prior-Fitted Networks | Dongwoo Lee, Dong Bok Lee, Steven Adriaensen, Juho Lee, Sung Ju Hwang, Frank Hutter, Seon Joo Kim, Hae Beom Lee |
| FairPFN: A Tabular Foundation Model for Causal Fairness | Jake Robertson, Noor Awad, Noah Hollmann, Frank Hutter, Samuel Gabriel Müller |
| Tuning LLM Judge Design Decisions for 1/1000 of the Cost | David Salinas, Omar Swelam, Frank Hutter |
| Position: The Future of Bayesian Prediction Is Prior-Fitted | Samuel Gabriel Müller, Arik Reuter, Noah Hollmann, David Rügamer, Frank Hutter |
| From Low Rank Gradient Subspace Stabilization to Low-Rank Weights: Observations, Theories, and Applications | Ajay Jaiswal, Yifan Wang, Lu Yin, Shiwei Liu, Runjin Chen, Jiawei Zhao, Ananth Grama, Yuandong Tian, Zhangyang “Atlas” Wang |
| LIFT the Veil for the Truth: Principal Weights Emerge after Rank Reduction for Reasoning-Focused Supervised Fine-Tuning | Zihang Liu, Tianyu Pang, Oleg Balabanov, Chaoqun Yang, Tianjin Huang, Lu Yin, Yaoqing Yang, Shiwei Liu |
| Mask-Enhanced Autoregressive Prediction: Pay Less Attention to Learn More | Xialie Zhuang, Zhikai Jia, Jianjin Li, Zhenyu Zhang, Li Shen, Zheng Cao, Shiwei Liu |