arxiv:2510.09608
YukangChen
Yukang
AI & ML interests
Efficient and Long AI
Recent Activity
updated a model about 17 hours ago
Perflow-Shuai/logs_5B_sp_32data_bs16_fromwan_svi_full_v2_fullattn_8nodes_64s_step600_ema published a model about 17 hours ago
Perflow-Shuai/logs_5B_sp_32data_bs16_fromwan_svi_full_v2_fullattn_8nodes_64s_step600_ema updated a model about 23 hours ago
Perflow-Shuai/logs_5B_sp_32data_bs16_fromwan_svi_full_v2_fullattn_8nodes_64s_step600Organizations
models 39
Yukang/Qwen2.5-32B-Open-R1-GRPO
Text Generation • 33B • Updated • 7
Yukang/Qwen2.5-7B-Open-R1-GRPO
Text Generation • 8B • Updated • 269
Yukang/Qwen2.5-14B-Open-R1-GRPO
15B • Updated • 47
Yukang/Qwen2.5-3B-Open-R1-GRPO
Text Generation • 3B • Updated • 52
Yukang/Qwen2.5-3B-Open-R1-Code-GRPO
Text Generation • 3B • Updated • 17
Yukang/DeepSeek-R1-Distill-Qwen-1.5B-GRPO
Text Generation • 2B • Updated • 2
Yukang/OpenR1-Distill-7B
Updated
Yukang/zephyr-7b-sft-full
Text Generation • Updated • 5
Yukang/zephyr-7b-dpo-full
Text Generation • Updated • 11 • 1
Yukang/zephyr-7b-gemma-dpo
Updated