publications

2026

1. Robust and Efficient Continual Model Merging via Global Singular Subspace Separation and Restoration

   Juncheol Shin, Byeongho Yu, Semin Kim, and Eunhyeok Park

   NeurIPS 2026 arXiv · Coming soon Code · Coming soon
2. LoopCD: Loop-wise Contrastive Decoding for Improving Reasoning in Looped Language Models

   Byeongho Yu^*, Junhyuk So^*, and Eunhyeok Park

   EMNLP 2026 Main Conference arXiv Code

2025

1. PruneCD: Contrasting Pruned Self Model to Improve Decoding Factuality

   Byeongho Yu^*, Changhun Lee^*, Jungyu Jin, and Eunhyeok Park

   EMNLP 2025 Main Conference arXiv Code
2. Stabilizing Direct Training of Spiking Neural Networks: Membrane Potential Initialization and Threshold-robust Surrogate Gradient

   Hyunho Kook, Byeongho Yu, Jeong Min Oh, and Eunhyeok Park

   WACV 2026 arXiv Code