qingyangzhang/Qwen3-8B-EM-AIME-Actor
8B • Updated • 7
qingyang zhang
qingyangzhang
AI & ML interests
RL
Recent Activity
upvoted a paper about 3 hours ago
Iris: Climbing to the Search Frontier published a dataset about 5 hours ago
qingyangzhang/QFT-OLMo-3-7B-Think updated a dataset about 6 hours ago
qingyangzhang/QFT-OLMo-3-7B-ThinkOrganizations
None yet
qingyangzhang/Qwen3-8B-AIME-TTRL-Actor
8B • Updated • 9
qingyangzhang/Qwen3-8B-PPO-Actor
8B • Updated • 8
qingyangzhang/Qwen3-8B-AIME-EMPO-Actor
Updated
qingyangzhang/Qwen3-8B-EMPO-Actor
Updated
qingyangzhang/Qwen3-14B-EM-320-Actor
15B • Updated • 5
qingyangzhang/Qwen3-14B-EM-224-Actor
15B • Updated • 5
qingyangzhang/OLMO3-7B-Zero-192-Critic
7B • Updated • 8
qingyangzhang/OLMO3-7B-Zero-192-Actor
7B • Updated • 12
qingyangzhang/Qwen3-7B-STPO-AIME-320
8B • Updated • 9
qingyangzhang/OLMO3-7B-TEMPO-AIME-320
7B • Updated • 9
qingyangzhang/Qwen3-14B-PPO-DAPO-17K-224-Critic
15B • Updated • 8
qingyangzhang/Qwen3-14B-PPO-DAPO-17K-224-Actor
15B • Updated • 5
qingyangzhang/Qwen3-14B-PPO-224-Actor
Updated
qingyangzhang/EMPO-Qwen2.5-Math-7B
8B • Updated • 11
qingyangzhang/EMPO-Qwen2.5-Math-1.5B
2B • Updated • 11
qingyangzhang/EMPO-OctoThinker-Long-Base-3B
4B • Updated • 7
qingyangzhang/Qwen2.5-1.5B-EMPO-NM-COT-20K-0614
2B • Updated • 2
qingyangzhang/Qwen2.5-1.5B-EMPO-NM-COT-20K
2B • Updated • 4
qingyangzhang/Qwen2.5-3B-EMPO-Natural-Reasoning
3B • Updated • 3
qingyangzhang/Qwen2.5-3B-EMPO-Natural-Reasoning-STEM-20K-short-answer
Text Generation • 3B • Updated • 10
qingyangzhang/Qwen2.5-3B-EMPO-Natural-Reasoning-STEM-25K-short-answer
3B • Updated • 5
qingyangzhang/Qwen2.5-3B-EMPO-Natural-Reasoning-50K
3B • Updated • 4 • 1
qingyangzhang/Qwen2.5-7B-EMPO-NM-COT-0320
Updated
qingyangzhang/Qwen2.5-1.5B-EMPO-NM-COT-0320
Updated
qingyangzhang/Qwen2.5-1.5B-EMPO-NM-COT-0314
Text Generation • 2B • Updated • 12
qingyangzhang/Qwen2.5-1.5B-EMPO-NM-COT
2B • Updated • 12
qingyangzhang/Qwen2.5-1.5B-Open-R1-GRPO-NM
Text Generation • 2B • Updated • 6