arxiv:2510.09608
YukangChen
Yukang
AI & ML interests
Efficient and Long AI
Recent Activity
upvoted a paper about 1 month ago
Smaller Models are Natural Explorers for Policy-Level Diversity in GRPOOrganizations
models 39
Yukang/Qwen2.5-32B-Open-R1-GRPO
Text Generation • 33B • Updated • 3
Yukang/Qwen2.5-7B-Open-R1-GRPO
Text Generation • 8B • Updated • 193 •
Yukang/Qwen2.5-14B-Open-R1-GRPO
15B • Updated • 4
Yukang/Qwen2.5-3B-Open-R1-GRPO
Text Generation • 3B • Updated • 11
Yukang/Qwen2.5-3B-Open-R1-Code-GRPO
Text Generation • 3B • Updated • 30
Yukang/DeepSeek-R1-Distill-Qwen-1.5B-GRPO
Text Generation • 2B • Updated • 7
Yukang/OpenR1-Distill-7B
Updated
Yukang/zephyr-7b-sft-full
Text Generation • Updated • 3
Yukang/zephyr-7b-dpo-full
Text Generation • Updated • 4 • 1
Yukang/zephyr-7b-gemma-dpo
Updated