Communication-efficient heterogeneous federated learning for large language models: federated asymmetric adaptive LoRA fine-tuning

MEPO-SLM: multi-objective evolutionary prompt optimization for energy-efficient small language models on edge devices

MEPO-SLM is presented, a framework that reformulates prompt engineering for SLMs as a four-objective Pareto problem over task inaccuracy, and Phi-3-mini and Gemma-2B on English TriviaQA and Arabic medical QA, and TinyLlama-1.1B on TriviaQA only are evaluated.

Tuning Social Indexes on Training-Data

To help a (perhaps artificial) policy decider compare the performance of its (perhaps artificial) social agents, a type of abstract evaluation machine is presented that could be used in various concrete operative situations. Designed on a sequence of progressively more challenging objectives on the chain \documentclass...

Explainable Federated Learning for Trustworthy Thoracic Disease Detection Under Non-IID Data Distributions

Comparison of SHAP and Grad-CAM attribution maps confirms clinically coherent disease-specific localisation, and reveals monotonic performance degradation, identifying minimal regularisation as optimal for multi-label medical imaging.

Dictionary category-adaptive fisher discriminant dictionary learning

A Low-Complexity Modified Versoria Diffusion Algorithm for Correlated Data

Fast Algorithms for a Large-Scale File Aggregation Problem

Results show that OnGP provides a robust online solution with efficiencies close to the Best Fit algorithm, while OffGP matches the near-optimal performance of Best Fit Decreasing within a 1.036% margin, confirming their value for time-critical applications.