EPFL@NeurIPS 2026
NeurIPS logo© 2026 EPFL
The following EPFL papers have been accepted to this year conference on Neural Information Processing Systems (NeurIPS). Congratulatations!
40th (main) edition of NeurIPS will take place in Sydney, Australia, from December 6th to December 12th, 2026. The other two venues are Atlanta and Paris.
- Optimistic Dual Averaging Unifies Modern Optimizers by Thomas Pethick, Wanyun Xie, Roman Machacek, Volkan Cevher
- AcceleGrad#: Adaptive Geometry-Aware Acceleration by Hanka Goralija*, Francesco Tonin*, Kimon Antonakopoulos, Alp Yurtsever, Volkan Cevher
- Constrained Stochastic Spectral Preconditioning Converges for Nonconvex Objectives by Konstantinos Oikonomidis, Jan Quan, Kimon Antonakopoulos, Tony Silveti-Falls, Volkan Cevher*, Panagiotis Patrinos*
- When Does Interaction Help? Representational Tradeoffs in Value-Based Imitation Learning by Luca Viano, Antoine Moulin, Audrey Huang, Volkan Cevher, Philip Amortila, Dylan J Foster
- Why Routers Freeze: Infinite Width Learning Dynamics for Mixture of Experts by Anish Dhir, Volkan Cevher, Leena Chennuru Vankadara
- Split the Differences, Pool the Rest: Provably Efficient Multi-Objective Imitation by Ziyad Sheebaelhamd, Luca Viano, Volkan Cevher, Claire Vernade
- Raven: High-Recall Sequence Modeling via Sparse Memory Routing by Arshia Afzal, Aviv Bick, Eric P. Xing, Volkan Cevher, Albert Gu
- Attention-Discounted Adaptive Sampler for Masked Diffusion Language Models by Yusuf Sahin, Ahmed R. Saikia, Volkan Cevher, Paolo Favaro
- Rescaled Asynchronous SGD: Optimal Distributed Optimization under Data and System Heterogeneity by Ammar Mahran, Artavazd Maranjyan, Peter Richtárik
- LOSCAR-SGD: Local SGD with Communication-Computation Overlap and Delay-Corrected Sparse Model Averaging by Yassine Maziane, Ammar Mahran, Artavazd Maranjyan, Peter Richtárik
- TempoPFN: Synthetic Pre-training of Linear RNNs for Zero-shot Time Series Forecasting by Vladyslav Moroshan, Julien Siems, Arber Zela, Timur Carstensen, Frank Hutter
- Scaling Laws for Multimodal Data Mixtures by Aditi Khandelwal*, Ayush Kumar Tarun*, Yixuan Xu, Imanol Schlag, Golnoosh Farnadi, Siva Reddy, Luke Zettlemoyer, Antoine Bosselut
- On Reparameterizing the Score Function by Mohammad Hossein Amani, Leonardo Bocchieri, Maxime Peyrard, Clément Hongler, Robert West
- The Future of Facts: Tracing the Factual Generation-Verification Gap by Tim R. Davidson*, Anja Surina*, Caglar Gulcehre
- Consolidating Reasoning with Test-Time Learning by Haotian Wu, Zeming Chen, Hao Zhao, Antoine Bosselut
- Tracing Persona Vectors Through LLM Pretraining by Viktor Moskvoretskii, Dominik Glandorf, Jorge Medina Moreira, Tanja Käser, Robert West
- Rethinking Projector Training in Multimodal LLMs by Fabian Gröger*, Naël Ouerghemi*, Shuo, Wen*, Maria Brbić
- To Align or Not to Align: Check Your COMPASS Before You Train by Fabian Gröger*, Petar Damjanović*, Maria Brbić
- MUX: Continuous Reasoning via Multiplexed Tokens by Ayhan Suleymanzade, Halil Alperen Gozeten, Michael M. Bronstein, Ismail Ilkan Ceylan, Jinwoo Kim
- Causal heteroscedastic structure learning from incomplete temporal data by Abdellah Rahmani, Pascal Frossard
- Stabilizing Extrapolation in Looped Transformers via Learned Stochastic Stopping by Hsun-Yu Kuo, El Mahdi Chayti, Patrik Reizinger, Wieland Brendel, Martin Jaggi
- Stochastic Optimization with Random Search by El Mahdi Chayti, Taha El Bakkali El Kadi, Omar Saadi, Martin Jaggi
- Stochastic Zeroth-Order Optimization Under Heavy-Tailed Noise by Taha El Bakkali El Kadi, El Mahdi Chayti, Qiuyi Zhang, Imane Rahali, Omar Saadi
- Joint Consistency: A Unified Test-Time Aggregation Framework via Energy Minimization by Yunzhen Yao, Hongye Wang, Yahong Wang, Michael Gastpar, Bo Jiang, Lie He
- PriFT: Prior-Support Guided Supervised Fine-Tuning by Ke Wang*, Shuangqi Li*, Mathieu Salzmann, Pascal Frossard
- LoRIF: Low-Rank Influence Functions for Scalable Training Data Attribution by Shuangqi Li, Hieu Le, Jingyi Xu, Mathieu Salzmann
- Support Before Frequency in Discrete Diffusion by Adrian Müller, Antoine Gonon, Zebang Shen, Ya-Ping Hsieh, Niao He
- Fixed-Point Masked Generative Modeling by Andrea Miele, Yiming QIN, Alba Carballo-Castro, Justin Deschenaux, Pascal Frossard
- It's All Training: A Fully Synthetic Single-Stage Recipe for LLMs by Pierre-Carl Langlais, Pieter Delobelle, Yannick Detrois, Pavel Chizhov, Carlos Rosas Hinostroza, Neil Si Smail, Benjamin Burtin, Hanna Shcharbakova, Ivan P. Yamshchikov, Anastasia Stasenko
- Breaking Adversarial Transferability in Fine-Tuned Speech Recognition by Mojtaba Nafez*, Aref Mousavi*, Mohammad Ebrahim Mahdavi, Mobina Poulaei, Kiarash Kiani Feriz, Mohammad Hossein Rohban
- Your Neighbors Know: Leveraging Local Neighborhoods for Backdoor Detection in Decentralized Learning by Sayan Biswas, Antoine Boutet, Davide Frey, Romaric Gaudel, Rachid Guerraoui, Maxime Jacovella, Anne-Marie Kermarrec, Dimitri Lerévérend, Francois Taiani, Martijn de Vos
- AgentWeave: Efficient Distributed Agent Serving via Flow Decomposition by Kaibin Guo, Pengtu Li, Zicong Hong*, Zhiyuan Fang, Wuhui Chen, Rachid Guerraoui, Anne-Marie Kermarrec
- Drift-React: One-step Generation of Reaction Pathways via SE(3) Drifting Fields by Rémi Schlama, Philippe Schwaller
- Robust and Scalable Collaborative Learning via Pull-Based Epidemic Communication by Abdellah El Mrini, Sadegh Farhadkhani, Rachid Guerraoui
- Zeroth-Order Stackelberg Control in Combinatorial Congestion Games by Saeed Masiha, Sepehr Elahi, Negar Kiyavash, Patrick Thiran
- Select-then-differentiate: Solving Bilevel Optimization with Manifold Lower-level Solution Sets by Saeed Masiha, Zebang Shen, Negar Kiyavash, Niao He
- RePercENT: Scaling Disentangled Representation Learning Beyond Two Modalities by Vasiliki Rizou, Pascal Frossard, Dorina Thanou
- Hierarchical Regime-Conditioned Dynamics for Spatiotemporal Graphs by Jeremy Baffou, Pascal Frossard, Dorina Thanou
- Hierarchical Graph Representation Learning with Pooling-Induced Substructures by Luca Sbicego, Xiaowen Dong, Dorina Thanou
- Benchmarking Optimizers for Large Language Model Pretraining by Andrei Semenov, Matteo Pagliardini, Martin Jaggi
- Learn from your own latents and not from tokens: A sample-complexity theory by Daniel Korchinski, Alessandro Favero, Matthieu Wyart
- EverAnimate: Minute-Scale Human Animation via Latent Flow Restoration by Wuyang Li*, Yang Gao*, Mariam Hassan, Lan Feng, Wentao Pan, Po-Chien Luan, Alexandre Alahi
- Drift-Resistant Navigation World Model with Anchored Epipolar Guidance by Po-Chien Luan, Zimin Xia, Wuyang Li, Yang Gao, Alexandre Alahi
- Pure Exploration Beyond Reward Feedback: The Role of Post-Action Context by Mohammad Shahverdikondori, Amir Mohammad Abouei, Alireza Rezaeimoghadam, Negar Kiyavash
- Active Context Selection Improves Simple Regret in Contextual Bandits by Mohammad Shahverdikondori, Jalal Etesami, Negar Kiyavash
- NEvo: Neural-Guided Evolutionary Video Synthesis for Dynamic Visual Selectivity by Yingtian Tang, Sogand Salehi, Ming Zhou, Amir Zamir, Leyla Isik, Martin Schrimpf
- Accuracy of Noise Ceiling Estimators for Brain Scores by Aude Maier, Lucas Gruaz, Martin Schrimpf, Johanni Brea
- MIRAGE: Adaptive Multimodal Gating for Whole-Brain fMRI Encoding by Abdulkadir Gokce, Badr AlKhamissi, Martin Schrimpf
- Post-Processing Guarantees for Classification under Linear-Fractional Performance Metrics by Andrea Della Vecchia
- Learning What to Forget: Improving LLM Unlearning via Learned Token-Level Importance by Gizem Yüce*, Giorgos Nikolaou*, Nicolas Flammarion
- WildBox: A Dataset and Benchmark for Aerial Monocular 3D Detection of African Savanna Wildlife by Vandita Shukla, Kilian Meier, Lucie Laporte-Devylder, Camille Rondeau Saint-Jean, Jenna Marie Kline, Blair Roberts Costelloe, Devis Tuia, Fabio Remondino, Benjamin Risse
- MARBLE: an Agent Benchmark for Spatial Reasoning and Visual Abstraction by Yulun Jiang*, Naël Ouerghemi*, Yekun Chai, Maria Brbic, Michael Moor
- Scaling Genomic Language Modeling with Unified Corpus and Evaluation in Bacteria by Maciej Wiatrak, Samuel T. Horsfield, Aaron Weimann, Ramon Viñas Torné, Maria Ntemourtsidou, David Abelson, Adam Dinan, John A. Lees, Maria Brbic, R. Andres Floto
- Flow-Corrected Shape Optimization: Taming Manifold Drift in High-Dimensional 3D Models by Emilien Seiler, Nicolas Talabot, Yingxuan You, Federico Stella, Pascal Fua
- MoBayes: A Modular Bayesian Framework for Separating Reasoning from Language in Conversational Clinical Decision Support by Yusuf Kesmen*, Fay Elhassan*, Jiayi Ma*, Julien Stalhandske, Yena Chang, Alexandra V. Kulinkina, David Sasu, Akhil Arora, Lars Henning Klein, Mary-Anne Hartley
- Revisiting Multi-View Stereo: A Sequence-to-Sequence Formulation by Aoxiang Fan, Corentin Dumery, Nicolas Talabot, Pascal Fua
- Proprio: Latent Self-Scoring and Inference-Time Refinement for Physically Plausible Video Generation by Mariam Hassan, Kaouther Messaoud, Wuyang Li, Alexandre Alahi
- S2MDF: A Plug-And-Play Layer for Intersection-Free Multi-Object Signed Distance Fields by Deniz Sayin Mercadier*, Federico Stella*, Aurel Bizeau, Nicolas Talabot, Pascal Fua
- Extracting Governing Equations from Latent Dynamics via Multi-View Contrastive Learning by Paolo Muratore, Mackenzie Weygandt Mathis
- Beyond Accuracy: A Diagnostic Benchmark for Hypothesis-Driven Experiment Planning in LLM Agents by Ryo Kuroki, Amin Mansouri, Philippe Schwaller
- Fed-SB: A Silver Bullet for Extreme Communication Efficiency and Performance in (Private) Federated LoRA Fine-Tuning by Raghav Singhal*, Kaustubh Ponkshe*, Rohit Vartak, Lav R. Varshney, Praneeth Vepakomma
- Brenier Meets Adversarial Training: Optimal Transport Geometry for Robust Learning by Alireza Abdollahpoorrostam*, Ehsan Sharifian*, Buse Şen*, Marco Cuturi, Daniel Kuhn
- Soft-Radial Projection for Constrained End-to-End Learning by Philipp J. Schneider, Daniel Kuhn
- Hierarchical Concept Geometry in Language Representations Emerges from Word Co-occurrence by Andres Nava, Matthieu Wyart
- Diffuse AI Control on Fuzzy Tasks by Mikhail Terekhov, Caglar Gulcehre, Vivek Hebbar, Joe Benton
- Geometric Latent Reasoning Induces Shorter Generations in LLM by Shashi Kumar*, Yacouba Kaloga*, Petr Motlicek, Ina Kodrasi, Andrea Cavallaro
- Better Language Models Require Better Domain-Specific Inductive Biases by Damien Teney, Liangze Jiang, Zachary Shinnick, Hemanth Saratchandran, Simon Lucey
- Recovering the Apresjan Hierarchy Using Linkage-Based Clustering by Maximilien Dreveton, Daichi Kuroda, Matthias Grossglauser, Patrick Thiran