collaborators

5 papers

cs.LG2026

Ghosted Layers: Unconstrained Activation Alignment for Recovering Layer-Pruned LLMs

Vincent-Daniel Yun, Junhyuk Jo, Sai Praneeth Karimireddy +1

Layer pruning removes entire Transformer decoder blocks from large language models, but introduces a mismatch between the hidden state received by the next surviving layer and the…

cs.LG2026

Weight Concentration Regularization for Improving Pruning Robustness Under High Sparsity

Vincent-Daniel Yun, Junhyuk Jo, Sunwoo Lee

Deep neural networks achieve outstanding performance across vision and language tasks, yet their large parameter counts limit deployment in resource-constrained settings. One-shot…

cs.LG2026

Biased Local SGD for Efficient Deep Learning on Heterogeneous Systems

Jihyun Lim, Junhyuk Jo, Chanhyeok Ko +3

Most parallel neural network training methods assume homogeneous computing resources. For example, synchronous data-parallel SGD suffers from significant synchronization overhead u…

cs.LG2026

Enabling Weak Client Participation via On-device Knowledge Distillation in Heterogeneous Federated Learning

Jihyun Lim, Junhyuk Jo, Tuo Zhang +1

Online Knowledge Distillation (KD) is recently highlighted to train large models in Federated Learning (FL) environments. Many existing studies adopt the logit ensemble method to p…

cs.LG2025

Asynchronous Sharpness-Aware Minimization For Fast and Accurate Deep Learning

Junhyuk Jo, Jihyun Lim, Sunwoo Lee

Sharpness-Aware Minimization (SAM) is an optimization method that improves generalization performance of machine learning models. Despite its superior generalization, SAM has not b…