arxiv:2510.01427
Sipeng Zhang
SipengZ
AI & ML interests
None yet
Organizations
None yet
models 11
SipengZ/rloo_beta0.05_Qwen2.5_iter3_fromywz
8B • Updated • 4
SipengZ/rloo_beta0.05_Qwen2.5_iter2_fromywz
8B • Updated • 3
SipengZ/rloo_beta0.05_Qwen2.5_iter1_fromywz
8B • Updated • 4
SipengZ/rapo_RPO_Qwen2.5_iter3_fromywz
8B • Updated • 7
SipengZ/rapo_RPO_Qwen2.5_iter2_fromywz
8B • Updated • 5
SipengZ/rapo_RPO_Qwen2.5_iter1_fromywz
8B • Updated
SipengZ/DPO_maxmin_Qwen7B
Updated
SipengZ/Qwen2.5-7B-Instruct_v10
Updated
SipengZ/Qwen2.5-3B-DPO
3B • Updated • 4
SipengZ/SFT
8B • Updated • 3
datasets 0
None public yet