EPFL Pre-NeurIPS 2025 Regional Event

The EPFL ELLIS Lausanne Unit, hosted within the EPFL AI Center, is delighted to invite you to its 2025 pre-NeurIPS regional event on November 24, 2025. This event is in anticipation of the upcoming NeurIPS Conference, which will be held in San Diego, USA, from December 2nd to December 7th and Mexico City, Mexico, from November 30th to December 5th.

While the conference is highly selective, 53 EPFL papers have been accepted to this year conference. The list of NeurIPS 2025 accepted papers with at least one EPFL author is available HERE.

For the fifth consecutive year we have decided, prior to the conference, to organize a local mid-scale event on the EPFL campus, and to invite anyone who had an accepted contribution – papers, talks, posters, workshops..- at NeurIPS to apply for one of our talk* and/or poster slots**. 

Beyond celebrating EPFL’s NeurIPS contributions, this event aims to:

• Foster exchange within the EPFL ML/AI community, helping researchers discover what others are working on and encouraging new collaborations;
• Connect local and external researchers interested in machine learning through discussions and networking.

• Talk submission: November 9
• Registration and poster submission: November 19

• With Limited Data for Multimodal Alignment, Let the STRUCTURE Guide You – by Shuo Wen & Fabian Gröger (MLBio)
• Flat Channels to Infinity in Neural Loss Landscapes – by Flavio Martinelli (LCN)
• FlashMD: Long-stride, Universal Prediction of Molecular Dynamics – by Filippo Bigi (COSMO)
• Inference-time Adaptive Tokenization via Online Compression – by Saibo Geng (DLab)

• Flow based approach for Dynamic Temporal Causal models with non-Gaussian or Heteroscedastic Noises – by Abdellah Rahmani (LTS4)
• Quantile Reward Policy Optimization: Alignment with Pointwise Regression and Exact Partition Functions – by Skander Moalla & Semen Matrenok (CLAIRE)
• The Nuclear Route: Sharp Asymptotics of ERM in Overparameterized Quadratic Networks – by Vittorio Erba (SPOC)
• Which Algorithms Have Tight Generalization Bounds? – by Thomas Weinberger (LTHC)