@article{weightedrewardpreferenceoptimizationfor, title = {Weighted-Reward Preference Optimization for Implicit Model Fusion}, author = {ZiYi Yang and Fanqi Wan and Longguang Zhong and Tianyuan Shi and Xiaojun Quan}, year = {2024}, eprint = {2412.03187}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2412.03187v1}, }