5 papers
Geometric Characterisation and Structured Trajectory Surrogates for Clinical Dataset Condensation
Pafue Christy Nganjimi, Andrew Soltan, Danielle Belgrave +3
Dataset condensation constructs compact synthetic datasets that retain the training utility of large real-world datasets, enabling efficient model development and potentially suppo…
Democratising Clinical AI through Dataset Condensation for Classical Clinical Models
Anshul Thakur, Soheila Molaei, Pafue Christy Nganjimi +5
Dataset condensation (DC) learns a compact synthetic dataset that enables models to match the performance of full-data training, prioritising utility over distributional fidelity.…
Geometric Uncertainty for Detecting and Correcting Hallucinations in LLMs
Edward Phillips, Sean Wu, Soheila Molaei +3
Large language models demonstrate impressive results across diverse tasks but are still known to hallucinate, generating linguistically plausible but incorrect answers to questions…
Improving Clinical Dataset Condensation with Mode Connectivity-based Trajectory Surrogates
Pafue Christy Nganjimi, Andrew Soltan, Danielle Belgrave +3
Dataset condensation (DC) enables the creation of compact, privacy-preserving synthetic datasets that can match the utility of real patient records, supporting democratised access…
Aggregation on Learnable Manifolds for Asynchronous Federated Optimization
Archie Licudi, Anshul Thakur, Soheila Molaei +2
Asynchronous federated learning (FL) with heterogeneous clients faces two key issues: curvature-induced loss barriers encountered by standard linear parameter interpolation techniq…