collaborators

5 papers

cs.LG2026

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…

cs.LG2026

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.…

cs.CL2025

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…

cs.LG2025

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…

cs.LG2025

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…