NeurIPS 2025

The team will be present at NeurIPS 2025!

Our team will be presenting the following works at the NeurIPS conference:

• Robust Distributed Estimation: Extending Gossip Algorithms to Ranking and Trimmed Means by Anna Van Elst, Igor Colin, Stefan Clémencon (arxiv paper)
• The quest for the GRAph Level autoEncoder (GRALE) by Paul Krzakala, Gabriel Melo, Charlotte Laclau, Florence d’Alché-Buc, Rémi Flamary (arxiv paper)
• Active Seriation by James Cheshire and Yann Issartel
• A Theoretical Framework for Grokking: Interpolation followed by Riemannian Norm Minimisation by Etienne Boursier, Scott Pesme, Radu-Alexandru Dragomir (arxiv paper)
• Self-Supervised Learning of Graph Representations for Network Intrusion Detection by Lorenzo Guerra, Thomas Chapuis, Guillaume Duc, Pavlo Mozharovskyi, Van-Tam Nguyen.

Also congratulations to our floor neighbors, the Multimedia and Image teams, on their NeurIPS papers!

• Continuous Simplicial Neural Networks by Aref Einizade, Dorina Thanou, Fragkiskos D. Malliaros, and Jhony H. Giraldo
• Concept-Guided Interpretability via Neural Chunking by Shuchen Wu, Stephan Alaniz, Shyamgopal Karthik, Peter Dayan, Eric Schulz, Zeynep Akata
• Diffusing DeBias: Synthetic Bias Amplification for Model Debiasing by Massimiliano Ciranni, Vito Paolo Pastore, Roberto Di Via, Enzo Tartaglione, Francesca Odone, Vittorio Murino
• From stability of Langevin diffusion to convergence of proximal MCMC for non-log-concave sampling by Marien Renaud, Valentin De Bortoli, Arthur Leclaire, Nicolas Papadakis.