Sunbeom Jeong

An Adaptive Sampling Framework for Diffusion-based Dataset Distillation with High Fidelity and Diversity

Dataset distillation (DD) aims to generate a compact synthetic dataset that enables efficient training of neural networks while maintaining performance comparable to that achieved with the original dataset. However, existing methods often suffer from two main limitations. They either rely on computa

Passive Torsional Compliance for Dynamic Stability Improvement of a Curved-Spoke Tri-Wheel

Domain-Aware Fine-Tuning: Enhancing Neural Network Adaptability

Fine-tuning pre-trained neural network models has become a widely adopted approach across various domains. However, it can lead to the distortion of pre-trained feature extractors that already possess strong generalization capabilities. Mitigating feature distortion during adaptation to new target d…