Fu, L., & Xue, Y. (2025). UMM-RM: An Upcycle-and-Merge MoE Reward Model for Mitigating Reward Hacking.
Chicago Style (17th ed.) CitationFu, Lingling, and Yongfu Xue. UMM-RM: An Upcycle-and-Merge MoE Reward Model for Mitigating Reward Hacking. 2025.
MLA (9th ed.) CitationFu, Lingling, and Yongfu Xue. UMM-RM: An Upcycle-and-Merge MoE Reward Model for Mitigating Reward Hacking. 2025.
Warning: These citations may not always be 100% accurate.