EPFL @ ICLR 2026

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

1. Selective Rotary Position Embedding by Sajad Movahedi, Arshia Afzal, Timur Carstensen, Frank Hutter, Antonio Orvieto, Volkan Cevher
2. Matching multiple experts: on the exploitability of multi-agent imitation learning by Antoine Bergerault, Volkan Cevher, Negar Mehr
3. ABBA-Adapters: Efficient and Expressive Fine-Tuning of Foundation Models by Raghav Singhal*, Kaustubh Ponkshe*, Rohit Vartak*, Praneeth Vepakomma
4. Safety Subspaces are Not Linearly Distinct: A Fine-Tuning Case Study by Kaustubh Ponkshe*, Shaan Shah*, Raghav Singhal*, Praneeth Vepakomma
5. Scaling Laws and Spectra of Shallow Neural Networks in the Feature Learning Regime by Leonardo Defilippis, Yizhou Xu, Julius Girardin, Vittorio Erba, Emanuele Troiani, Lenka Zdeborová, Bruno Loureiro, Florent Krzakala
6. Efficient Best-of-Both-Worlds Algorithms for Contextual Combinatorial Semi-Bandits by Mengmeng Li, Philipp J. Schneider, Jelisaveta Aleksic, Daniel Kuhn
7. PERK: Long-Context Reasoning as Parameter-Efficient Test-Time Learning by Zeming Chen, Angelika Romanou, Gail Weiss, Antoine Bosselut
8. GeoFAR: Geography-informed frequency-aware super-resolution for climate data by Chang Xu, Gencer Sumbuel, Li Mi, Robin Zbinden, and Devis Tuia
9. Learning to Weight Parameters for Data Attribution by Shuangqi Li, Hieu Le, Jingyi Xu, Mathieu Salzmann
10. Weight Decay may matter more than µP for Learning Rate Transfer in Practice by Atli Kosson, Jeremy Welborn, Yang Liu, Martin Jaggi, Xi Chen
11. MIAM: Modality Imbalance-Aware Masking for Multimodal Ecological Applications by Robin Zbinden*, Wesley Monteith-Finas*, Gencer Sumbuel, Nina van Tiel, Chiara Vanalli, and Devis Tuia
12. LLaVAction: evaluating and training multi-modal large language models for action understanding by Haozhe Qi*, Shaokai Ye*, Alexander Mathis, Mackenzie Weygandt Mathis
13. RL for Reasoning by Adaptively Revealing Rationales by Mohammad Hossein Amani, Aryo Lotfi, Nicolas Baldwin, Samy Bengio, Mehrdad Farajtabar, Emmanuel Abbe, Robert West
14. Narrow Finetuning Leaves Clearly Readable Traces in the Activation Differences by Julian Minder, Clément Dumas, Stewart Slocum, Helena Casademunt, Cameron Holmes, Robert West, Neel Nanda
15. Navigating the Accuracy-Size Trade-Off with Flexible Model Merging by Akash Dhasade, Divyansh Jhunjhunwala, Milos Vujasinovic, Gauri Joshi, Anne-Marie Kermarrec
16. Robust Federated Inference by Akash Dhasade, Sadegh Farhadkhani, Rachid Guerraoui, Nirupam Gupta, Maxime Jacovella, Anne-Marie Kermarrec, Rafael Pinot
17. HeurekaBench: A Benchmarking Framework for AI Co-scientist by Siba Smarak Panigrahi*, Jovana Videnovic*, Maria Brbic
18. When LLMs Speak with Confidence, Preference Alignment Gets Stronger by Myeongho Jeon*, Amirabbas Afzali*, Maria Brbic
19. Meta-RL Induces Exploration in Language Agents by Yulun Jiang*, Liangze Jiang*, Damien Teney, Michael Moor, Maria Brbic
20. Optimizing Agent Planning for Security and Autonomy by Aashish Kolluri, Rishi Sharma, Manuel Costa, Boris Köpf, Tobias Nießen, Mark Russinovich, Shruti Tople, Santiago Zanella-Beguelin
21. Mixture of Cognitive Reasoners: Modular Reasoning with Brain-Like Specialization by Badr AlKhamissi, C. Nicolò De Sabbata, Greta Tuckute, Zeming Chen, Martin Schrimpf, Antoine Bosselut
22. Inducing Dyslexia in Vision Language Models by Melika Honarmand, Ayati Sharma, Badr AlKhamissi, Johannes Mehrer, Martin Schrimpf
23. Model-Guided Microstimulation Steers Primate Visual Behavior by Johannes Mehrer, Ben Lonnqvist, Abdülkadir Gökce, Anna Mitola, Paolo Papale, Martin Schrimpf
24. Generating Directed Graphs with Dual Attention and Asymmetric Encoding by Alba Carballo-Castro, Manuel Madeira, Yiming Qin, Dorina Thanou, Pascal Frossard
25. Symmetry-Aware Bayesian Optimization via Max Kernels by Anthony Bardou, Antoine Gonon, Aryan Ahadinia, Patrick Thiran
26. SynthWorlds: Controlled Parallel Worlds for Disentangling Reasoning and Knowledge in Language Models by Ken Gu, Advait Bhat, Mike A Merrill, Robert West, Xin Liu, Daniel McDuff, Tim Althoff
27. Partition Generative Modeling: Masked Modeling Without Masks by Justin Deschenaux, Lan Tran, Caglar Gulcehre
28. The Diffusion Duality, Chapter II: Ψ-Samplers and Efficient Curriculum by Justin Deschenaux, Caglar Gulcehre, Subham Sekhar Sahoo
29. Loopholing Discrete Diffusion: Deterministic Bypass of the Sampling Wall by Mingyu Jo, Jaesik Yoon, Justin Deschenaux, Caglar Gulcehre, Sungjin Ahn
30. Non-Asymptotic Analysis of Efficiency in Conformalized Regression by Yunzhen Yao, Lie He, Michael Gastpar
31. Lookup multivariate Kolmogorov-Arnold Networks by Sergey Pozdnyakov, Philippe Schwaller
32. Beyond URLs: Metadata Diversity and Position for Efficient LLM Pretraining by Dongyang Fan*, Diba Hashemi*, Sai Praneeth Karimireddy, Martin Jaggi
33. Multimodality As Supervision: Self-Supervised Specialization To The Test Environment Via Multimodality by Kunal Pratap Singh*, Ali Garjani*, Rishubh Singh, Muhammad Uzair Khattak, Jason Toskov, Efe Tarhan, Andrei Atanov, Oghuzan Fatih Kar, Amir Zamir
34. Gradient-Normalized Smoothness for Optimization with Inexact Hessians by Andrei Semenov, Martin Jaggi, Nikita Doikov
35. JointDiff: Bridging Continuous and Discrete in Multi-Agent Trajectory Generation by Guillem Capellera, Luis Ferraz, Antonio Rubio, Alexandre Alahi, Antonio Agudo
36. Loc2: Interpretable Cross-View Localization via Depth-Lifted Local Feature Matching by Zimin Xia*, Chenghao Xu*, Alexandre Alahi
37. LayerSync: Self-aligning Intermediate Layers by Yasaman Haghighi*, Bastien Van Delft*, Mariam Hassan, Alexandre Alahi
38. Stable video infinity: Infinite-length video generation with error recycling by Wuyang Li, Wentao Pan, Po-Chien Luan, Yang Gao, Alexandre Alahi
39. Rap: 3d rasterization augmented end-to-end planning by Lan Feng, Yang Gao, Eloi Zablocki, Quanyi Li, Wuyang Li, Sichao Liu, Matthieu Cord, Alexandre Alahi
40. From Markov to Laplace: How Mamba In-Context Learns Markov Chains by Marco Bondaschi, Ashok Vardhan Makkuva, Nived Rajaraman, Xiuying Wei, Razvan Pascanu, Caglar Gulcehre, Michael Gastpar
41. Faster Gradient Methods for Highly-smooth Stochastic Bilevel Optimization by Lesi Chen, Junru Li, El Mahdi Chayti, Jingzhao Zhang
42. How Well Does GPT-4o Understand Vision? Evaluating Multimodal Foundation Models on Standard Computer Vision Tasks by Rahul Ramachandran, Ali Garjani, Roman Bachmann, Andrei Atanov, Oğuzhan Fatih Kar, Amir Zamir
43. Can Transformers Really Do It All? On the Compatibility of Inductive Biases Across Tasks by Damien Teney, Liangze Jiang, Hemanth Saratchandran, Simon Lucey
44. AbstRaL: Augmenting LLMs' Reasoning by Reinforcing Abstract Thinking by Silin Gao, Antoine Bosselut, Samy Bengio, Emmanuel Abbe
45. Dataset Distillation for Memorized Data: Soft Labels can Leak Held-Out Teacher Knowledge by Freya Behrens, Lenka Zdeborová
46. Statistical Advantage of Softmax Attention: Insights from Single-Location Regression by Odilon Duranthon, Pierre Marion, Claire Boyer, Bruno Loureiro, Lenka Zdeborová
47. Control Tax: The Price of Keeping AI in Check by Mikhail Terekhov, Zhen Ning David Liu, Caglar Gulcehre, Samuel Albanie
48. Adaptive Attacks on Trusted Monitors Subvert AI Control Protocols by Mikhail Terekhov, Alexander Panfilov, Daniil Dzenhaliou, Caglar Gulcehre, Maksym Andriushchenko, Ameya Prabhu, Jonas Geiping
49. Geometry-aware Policy Imitation by Yiming Li, Nael Darwiche, Amirreza Razmjoo, Sichao Liu, Yilun Du, Auke Ijspeert, Sylvain Calinon
50. The Hot Mess of AI: How Does Misalignment Scale With Model Intelligence and Task Complexity? by Alexander Hägele, Aryo Pradipta Gema, Henry Sleight, Ethan Perez, Jascha Sohl-Dickstein

∗Shared first authorship and equal contributions.