Machine Learning

Congratulations to Moritz Golg whose paper “Var-JEPA: A Variational Formulation of the Joint-Embedding Predictive Architecture - Bridging Predictive and Generative Self-Supervised Learning” was accepted for presentation at ICML 2026. A preprint paper can be found on arXiv.

Congratulations to Natalia Hong whose paper “Imputation Free Deep Survival Prediction with Conditional Variational Autoencoders” was accepted for publication in the Journal of Healthcare Informatics Research.

• Multimodal Survival Analysis with Locally Deployable Large Language Models at the NeurIPS 2025 2nd Workshop on Multi-modal Foundation Models and Large Language Models for Life Sciences

We are very pleased to have contributed an article to the Association for Improvements in the Maternity Services (AIMS) journal entitled “Women, Pregnancy and Artificial Intelligence: Opportunities and Cautions in the Age of Digital Maternity” as part of the MuM-Predict consortium. The article demonstrates our commitment to connecting AI research to those it affects.

Congratulations to Ellen Visscher whose paper “Hybrid restricted master problem for Boolean matrix factorisation” was accepted for presentation at AAAI 2026. A preprint paper can be found on arXiv.

Congratulations to Hanwen Xing whose paper “Continual learning via probabilistic exchangeable sequence modelling” was accepted in Transactions on Machine Learning Research. A copy of the paper can be found on OpenReview.

Congratulations to Mortiz Gogl whose paper “DoseSurv: Predicting Personalized Survival Outcomes under Continuous-Valued Treatments” was accepted for NeurIPS 2025. A copy of the paper can be found on the NeurIPS25 website.

A preprint of work by Charles Gadd describing “SurvivEHR: a competing risks, time-to-event foundation model for multiple long-term conditions from primary care electronic health records” is now available on medRxiv.

“Multiple long-term conditions (MLTCs) or multimorbidity – the co-occurrence of multiple chronic conditions –presents a growing challenge for primary care. Current predictive models often target single outcomes and overlook the complexities of time-to-event risk in real-world, longitudinal health data. Here, we present SurvivEHR, a generative transformer-based foundation model trained on over 7.6 billion coded events from 23 million patients in UK primary care. SurvivEHR introduces a competing risk time-to-event pretraining objective that enables accurate forecasting of future diagnoses, investigations, medications, and mortality. We demonstrate that SurvivEHR achieves strong risk stratification performance, captures clinically meaningful trajectories, and outperforms benchmark survival models across multiple tasks. The model also transfers effectively to fine-tuned prognostic tasks, particularly in low-resource settings. By learning patient trajectories directly from routine health records, SurvivEHR offers a scalable and privacy-preserving approach for building generalisable clinical risk tools that address the complexity of MLTCs in primary care..”