LatentGym: A Testbed For Cross-Task Experiential Learning With Controllable Latent Structure

LatentGym uses environments with known latent structure to measure how LLM agents gather information and adapt across related tasks.

A Closer Look at Personalized Fine-Tuning in Heterogeneous Federated Learning

A study of federated feature distortion shows how linear probing followed by fine-tuning can improve the balance between client personalization and generalization.

FedSoup: Improving Generalization and Personalization in Federated Learning via Selective Model Interpolation

FedSoup uses selective model interpolation to balance local and global performance, reduce overfitting, and seek flat minima for improved generalization.