3 papers
cs.LG2025
FRAIN to Train: A Fast-and-Reliable Solution for Decentralized Federated Learning
Sanghyeon Park, Soo-Mook Moon
Federated learning (FL) enables collaborative model training across distributed clients while preserving data locality. Although FedAvg pioneered synchronous rounds for global mode…
cs.CR2025
RouTEE: A Secure Payment Network Routing Hub using Trusted Execution Environments
Junmo Lee, Seongjun Kim, Sanghyeon Park +1
Cryptocurrencies such as Bitcoin and Ethereum have made payment transactions possible without a trusted third party, but they have a scalability issue due to their consensus mechan…
cs.LG2025
CURing Large Models: Compression via CUR Decomposition
Sanghyeon Park, Soo-Mook Moon
Large deep learning models have achieved remarkable success but are resource-intensive, posing challenges such as memory usage. We introduce CURing, a novel model compression metho…