by Zirui Zhu Papers
3 papers found
MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch Training
Yang Luo, Zangwei Zheng, Ziheng Qin et al.
ICML 2025posterarXiv:2508.20577
SeedLoRA: A Fusion Approach to Efficient LLM Fine-Tuning
Yong Liu, Di Fu, Shenggan Cheng et al.
ICML 2025poster
Sparse MeZO: Less Parameters for Better Performance in Zeroth-Order LLM Fine-Tuning
Yong Liu, Zirui Zhu, Chaoyu Gong et al.
NeurIPS 2025posterarXiv:2402.15751
36
citations