Gen AI Hub at NeurIPS
NeurIPS takes place in San Diego, United States of America and home of Balboa Botanical Gardens (credit: Alex Hand, Unsplash)
Hub researchers have a strong presence at this year’s NeurIPS conference in San Diego, an annual international conference on Neural Information Processing Systems.
The Hub is sponsoring a workshop co-organised by José Miguel Hernández Lobato on Structured Probabilistic Inference & Generative Modelling: https://spigmworkshopv3.github.io/
Mark Plumbley will be presenting at a session on Generative and Protective AI for Content Creation: https://genprocc.github.io/
Aldo Faisal has co-authored a paper that will presented at a poster session by his colleague Filippo Valdettaro, https://neurips.cc/virtual/2025/loc/san-diego/poster/118430
Pasquale Minervini has two papers featuring at NeurIPS, including one spotlight:
Neurosymbolic Diffusion Models, https://arxiv.org/abs/2505.13138
MMLongBench: Benchmarking Long-Context Vision-Language Models Effectively and Thoroughly (spotlight), https://arxiv.org/abs/2505.10610
Arthur Gretton has five accepted NeurIPS papers, including two spotlights:
Demystifying Spectral Feature Learning for Instrumental Variable Regression
Regularized least squares learning with heavy-tailed noise is minimax optimal (spotlight)
Doubly-Robust Estimation of Counterfactual Policy Mean Embeddings
Density Ratio-Free Doubly Robust Proxy Causal Learning
On the Hardness of Conditional Independence Testing In Practice (spotlight)
