EPFL papers @ ICML 2025

Below is a list of ICML 2025 papers with at least one EPFL author:

1. IL-SOAR : Imitation Learning with Soft Optimistic Actor cRitic by Stefano Viel, Luca Viano, Volkan Cevher
2. Best of Both Worlds: Regret Minimization versus Minimax Play by Adrian Müller, Jon Schneider, Stratis Skoulakis, Luca Viano, Volkan Cevher
3. Continuous-Time Analysis of Heavy Ball Momentum in Min-Max Games by Yi Feng, Kaito Fujii, Stratis Skoulakis, Xiao Wang, Volkan Cevher
4. Layer-wise Quantization for Quantized Optimistic Dual Averaging by Anh Duc Nguyen, Ilia Markov, Zhengqing Wu, Ali Ramezani-Kebrya, Kimon Antonakopoulos, Dan Alistarh, Volkan Cevher
5. Chameleon: A Flexible Data-mixing Framework for Language Model Pretraining and Finetuning by Wanyun Xie, Francesco Tonin, Volkan Cevher
6. Accelerating Spectral Clustering under Fairness Constraints by Francesco Tonin, Alex Lambert, Johan Suykens, Volkan Cevher
7. Training Deep Learning Models with Norm-Constrained LMOs by Thomas Pethick, Wanyun Xie, Kimon Antonakopoulos, Zhenyu Zhu, Antonio Silveti-Falls, Volkan Cevher; (spotlight)
8. Generalization of noisy SGD in unbounded non-convex settings by Leello Tadesse Dadi, Volkan Cevher
9. Learn to Vaccinate: Combining Structure Learning and Effective Vaccination for Epidemic and Outbreak Control by Sepehr Elahi, Paula Mürmann, Patrick Thiran
10. IT^3 : Idempotent Test-Time Training by Nikita Durasov, Assaf Shocher, Doruk Oner, Gal Chechik, Alexei A Efros, Pascal Fua
11. Causal Effect Identification in lvLiNGAM from Higher-Order Cumulants by Daniele Tramontano, Yaroslav Kivva, Saber Salehkaleybar, Negar Kiyavash, Mathias Drton
12. Hierarchical Reinforcement Learning with Targeted Causal Interventions by Mohammadsadegh Khorasani, Saber Salehkaleybar, Negar Kiyavash, Matthias Grossglauser
13. The dark side of the forces: assessing non-conservative force models for atomistic machine learning by Filippo Bigi, Marcel Langer, Michele Ceriotti; (spotlight)
14. Fundamental limits of learning in sequence multi-index models and deep attention networks: high-dimensional asymptotics and sharp thresholds by Emanuele Troiani, Hugo Cui, Yatin Dandi, Florent Krzakala, Lenka Zdeborova
15. TAROT: Targeted Data Selection via Optimal Transport by Lan Feng, Fan Nie, Yuejiang Liu, Alexandre Alahi
16. Fleet of Agents: Coordinated Problem Solving with Large Language Models by Nearchos Potamitis, Lars Klein, Roland Aydin, Robert West, Caglar Gulcehre, Akhil Arora
17. Boosting Protein Graph Representations through Static-Dynamic Fusion by Pengkang Guo, Bruno Correia, Pierre Vandergheynst, Daniel Probst
18. Contour Integration Underlies Human-Like Vision by Ben Lonnqvist, Elsa Scialom, Abdulkadir Gokce, Zehra Merchant, Michael Herzog, Martin Schrimpf
19. QT-DoG: Quantization-Aware Training for Domain Generalization by Saqib Javed, Hieu Le, Mathieu Salzmann
20. Counting in small transformers: The delicate interplay between attention and feed-forward layers by Freya Behrens, Luca Biggio, Lenka Zdeborova
21. On-Device Collaborative Language Modeling via a Mixture of Generalists and Specialists by Dongyang Fan, Bettina Messmer, Nikita Doikov, Martin Jaggi
22. The Surprising Agreement Between Convex Optimization Theory and Learning-Rate Scheduling for Large Model Training by Fabian Schaipp, Alexander Hägele, Adrien Taylor, Umut Simsekli, Francis Bach
23. DeFoG: Discrete Flow Matching for Graph Generation by Yiming Qin, Manuel Madeira, Dorina Thanou, Pascal Frossard; (spotlight)
24. Fast inference with Kronecker-sparse matrices by Antoine Gonon, Léon Zheng, Pascal Carrivain, Quoc-Tung Le
25. A rescaling-invariant Lipschitz bound based on path-metrics for modern ReLU network parameterizations by Antoine Gonon, Nicolas Brisebarre, Elisa Riccietti, Rémi Gribonval
26. Leveraging Sparsity for Sample-Efficient Preference Learning: A Theoretical Perspective by Yunzhen Yao, Lie He, Michael Gastpar
27. How compositional generalization and creativity improve as diffusion models are trained by Alessandro Favero, Antonio Sclocchi, Francesco Cagnetta, Pascal Frossard, Matthieu Wyart
28. FlexTok: Resampling Images into 1D Token Sequences of Flexible Length by Roman Bachmann, Jesse Allardice, David Mizrahi, Enrico Fini, Oğuzhan Fatih Kar, Elmira Amirloo, Alaaeldin El-Nouby, Amir Zamir, Afshin Dehghan
29. MPO: An Efficient Post-Processing Framework for Mixing Diverse Preference Alignment by Tianze Wang, Dongnan Gui, Yifan Hu, Shuhang Lin, Linjun Zhang
30. Learning Parametric Distributions from Samples and Preferences by Marc Jourdan, Gizem Yüce, Nicolas Flammarion; (spotlight)
31. OOD-Chameleon: Is Algorithm Selection for OOD Generalization Learnable? by Liangze Jiang, Damien Teney
32. Learning In-context n-grams with Transformers: Sub-n-grams Are Near-stationary Points by Aditya Varre*, Gizem Yüce*, Nicolas Flammarion
33. Scaling Laws for Task-Optimized Models of the Primate Visual Ventral Stream by Abdulkadir Gokce, Martin Schrimpf; (spotlight)
34. Simplicity Bias and Optimization Threshold in Two-Layer Networks by Etienne Boursier, Nicolas Flammarion
35. The Diffusion Duality by Subham Sekhar Sahoo, Justin Deschenaux, Aaron Gokaslan, Guanghan Wang, Justin T Chiu, Volodymyr Kuleshov
36. Analytical Lyapunov Function Discovery: An RL-based Generative Approach by Haohan Zou*, Jie Feng*, Hao Zhao, Yuanyuan Shi
37. A New Approach to Backtracking Counterfactual Explanations: A Causal Framework for Efficient Model Interpretability by Pouria Fatemi, Ehsan Sharifian, Mohammad Hossein Yassaee
38. Towards Trustworthy Federated Learning with Untrusted Participants by Youssef Allouah, Rachid Guerraoui, John Stephan
39. Certified Unlearning for Neural Networks by Anastasia Koloskova*, Youssef Allouah*, Animesh Jha, Rachid Guerraoui, Sanmi Koyejo
40. Synthetic Face Datasets Generation via Latent Space Exploration from Brownian Identity Diffusion by David Geissbühler, Hatef Otroshi Shahreza, Sébastien Marcel
41. Robust ML Auditing using Prior Knowledge by Jade Garcia Bourrée, Augustin Godinot, Martijn De Vos, Milos Vujasinovic, Sayan Biswas, Gilles Tredan, Erwan Le Merrer, Anne-Marie Kermarrec

*Equal contribution