@article{dropupcyclingtrainingsparsemixtureof, title = {Drop-Upcycling: Training Sparse Mixture of Experts with Partial Re-initialization}, author = {Taishi Nakamura and Takuya Akiba and Kazuki Fujii and Yusuke Oda and Rio Yokota and Jun Suzuki}, year = {2025}, eprint = {2502.19261}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2502.19261v2}, }