EPFL @ ICML 2026

Below is a list of ICML 2026 papers with at least one EPFL author:

1. Spatial Priors via Space Filling Curves for Small and Limited Data Vision Transformers by Leyla Naz Candogan*, Arshia Afzal*, Pol Puigdemont, Volkan Cevher
2. On the Role of Batch Size in Stochastic Conditional Gradient Methods by Rustem Islamov, Roman Machacek, Aurelien Lucchi, Tony Silveti-Falls, Eduard Gorbunov, Volkan Cevher
3. Multi-agent imitation learning with function approximation: linear Markov games and beyond by Luca Viano, Till Freihaut, Emanuele Nevali, Volkan Cevher, Matthieu Geist, Giorgia Ramponi
4. Enhancing LLM Training via Spectral Clipping by Xiaowen Jiang, Andrei Semenov, Sebastian U. Stich
5. ScoreMix: Synthetic Data Generation by Score Composition in Diffusion Models Improves Recognition by Parsa Rahimi, Sebastien Marcel
6. Single-Head Attention in High Dimensions: A Theory of Generalization, Weights Spectra, and Scaling Laws by Fabrizio Boncoraglio, Vittorio Erba, Emanuele Troiani, Yizhou Xu, Florent Krzakala, Lenka Zdeborová
7. A Solvable High-Dimensional Model Where Nonlinear Autoencoders Learn Structure Invisible to PCA While Test Loss Misaligns With Generalization by Vicente Conde Mendes, Lorenzo Bardone, Cédric Koller, Jorge Medina Moreira, Vittorio Erba, Emanuele Troiani, Lenka Zdeborová
8. Can Local Learning Match Self-Supervised Backpropagation? by Wu S. Zihan, Ariane Delrocq, Wulfram Gerstner, Guillaume Bellec
9. Helpful to a Fault: Measuring Illicit Assistance in Multi-Turn, Multilingual LLM Agents by Nivya Talokar, Ayush Kumar Tarun, Murari Mandal, Maksym Andriushchenko, Antoine Bosselut
10. Schema-Guided World Modeling for Understanding Hierarchical Visual Dynamics by Silin Gao, Hao Zhao, Zeming Chen, Sepideh Mamooler, Antara Raaghavi Bhattacharya, Qiyu Wu, Hiromi Wakaki, Yuki Mitsufuji, Li Mi, Syrielle Montariol, Antoine Bosselut
11. Diversity Matters: Revisiting Test-Time Compute in Vision-Language Models by Yijie Tong, Yifan Hou, Shaobo Cui, Antoine Bosselut, Mrinmaya Sachan
12. Learning Randomized Reductions by Ferhat Erata, Orr Paradise, Thanos Typaldos, Timos Antonopoulos, ThanhVu Nguyen, Shafi Goldwasser, Ruzica Piskac
13. Revisiting the Platonic Representation Hypothesis: An Aristotelian View by Fabian Gröger*, Shuo Wen*, Maria Brbic
14. PACER: Acyclic Causal Discovery from Large-scale Interventional Data by Ramon Vinas Torne, Silvia Fabregas Salazar, Soyon Park, Ivo Ban, Artyom Gadetsky, Nikita Doikov, Maria Brbic
15. Induction Heads Interpolate N-Grams by Francesco D'Angelo, Oğuz Kaan Yüksel, Swathi Shree Narashiman, Nicolas Flammarion
16. Incremental Learning of Sparse Attention Patterns in Transformers by Oğuz Kaan Yüksel, Rodrigo Alvarez Lucendo, Nicolas Flammarion
17. Scaling Beyond Masked Diffusion Language Models by Subham Sekhar Sahoo, Jean-Marie Lemercier, Zhihan Yang, Justin Deschenaux, Jingyu Liu, John Thickstun, Ante Jukić
18. Time series saliency maps: Explaining models across multiple domains by Christodoulos Kechris, Jonathan Dan, David Atienza
19. Quantifying the Generalization Gap in Seizure Detection: A Large-Scale Empirical Benchmark via the SzCore Challenge by Jonathan Dan, Amirhossein Shahbazinia, Christodoulos Kechris, David Atienza
20. Helpful to a Fault: Measuring Illicit Assistance in Multi-Turn, Multilingual LLM Agents by Nivya Talokar, Ayush K Tarun, Murari Mandal, Maksym Andriushchenko, Antoine Bosselut
21. Scalable and Differentiable Point-Cloud Registration Using Maximum Mean Discrepancy by Rixon Crane, Fahira Afzal Maken, Nicholas Lawrance, Stanislav Funiak, Kasra Khosoussi, Ming Xu, Russell Tsuchida
22. Procedural Pretraining: Warming Up Language Models with Abstract Data by Liangze Jiang*, Zachary Shinnick*, Anton van den Hengel, Hemanth Saratchandran, Damien Teney
23. What Language is This? Ask Your Tokenizer. by Clara Meister, Ahmetcan Yavuz, Pietro Lesci, Tiago Pimentel
24. (1D) Ordered Tokens Enable Efficient Test-Time Search by Zhitong Gao, Parham Rezaei, Ali Cy, Mingqiao Ye, Nataša Jovanović, Jesse Allardice, Afshin Dehghan, Amir Zamir, Roman Bachmann, Oğuzhan Fatih Kar
25. MODUS: Decoder-only Any-to-Any Modeling of Diverse Modalities by Mingqiao Ye, Zhaochong An, Zhitong Gao, Xian Liu, Oğuzhan Fatih Kar, Jesse Allardice, Roman Bachmann, David Mizrahi, François Fleuret, Chuan Li, Amir Zadeh, Serge Belongie, Afshin Dehghan, Amir Zamir
26. RAT+: Train Dense, Infer Sparse - Recurrence Augmented Attention for Dilated by Xiuying Wei, Caglar Gulcehre
27. Nash Equilibria in Games with Playerwise Concave Coupling Constraints: Existence and Computation by Philip Jordan, Maryam Kamgarpour
28. Constrained Meta Reinforcement Learning with Provable Test-Time Safety by Tingting Ni, Maryam Kamgarpour
29. VideoFlexTok: Flexible-Length Coarse-to-Fine Video Tokenization by Andrei Atanov, Jesse Allardice, Roman Bachmann, Oğuzhan Fatih Kar, R Devon Hjelm, David Griffiths, Peter Fu, Afshin Dehghan, Amir Zamir
30. Error Propagation in Dynamic Programming: From Stochastic Control to American Option Pricing by Andrea Della Vecchia, Damir Filipovic