a-F1/R1_Qwen7B_0.005_20_easy
Updated
Chongyu Fan
a-F1
AI & ML interests
None yet
Recent Activity
authored a paper 3 days ago
UP: Unbounded Positive Asymmetric Optimization for Breaking the Exploration-Stability Dilemma authored a paper 3 days ago
Rethinking Muon Beyond Pretraining: Spectral Failures and High-Pass Remedies for VLA and RLVROrganizations
a-F1/R1_Qwen1.5B_0.005_10_Hard
2B • Updated • 1
a-F1/R1_Qwen7B_0.005_10_Hard
Updated
a-F1/R1_Qwen1.5B_0.005_10_Mid
2B • Updated • 1
a-F1/R1_Qwen7B_0.005_10_Mid
Updated
a-F1/R1_Qwen1.5B_0.005_10_easy
2B • Updated • 2
a-F1/R1_Qwen7B_0.005_10_easy
Updated
a-F1/R1_Qwen1.5B_0.005_5_Hard
2B • Updated • 1
a-F1/R1_Qwen7B_0.005_5_Hard
Updated
a-F1/R1_Qwen1.5B_0.005_5_Mid
2B • Updated • 2
a-F1/R1_Qwen7B_0.005_5_Mid
Updated
a-F1/R1_Qwen1.5B_0.005_5_easy
2B • Updated • 2
a-F1/R1_Qwen7B_0.005_5_easy
Updated
a-F1/R1_Qwen1.5B_0.001_40_Hard
2B • Updated • 2
a-F1/R1_Qwen7B_0.001_40_Hard
Updated
a-F1/R1_Qwen1.5B_0.001_40_Mid
2B • Updated • 2
a-F1/R1_Qwen7B_0.001_40_Mid
Updated
a-F1/R1_Qwen1.5B_0.001_40_easy
2B • Updated • 1
a-F1/R1_Qwen7B_0.001_40_easy
Updated
a-F1/R1_Qwen1.5B_0.001_20_Hard
2B • Updated • 1
a-F1/R1_Qwen7B_0.001_20_Hard
Updated
a-F1/R1_Qwen1.5B_0.001_20_Mid
2B • Updated • 1
a-F1/R1_Qwen7B_0.001_20_Mid
Updated
a-F1/R1_Qwen1.5B_0.001_20_easy
2B • Updated
a-F1/R1_Qwen7B_0.001_20_easy
Updated
a-F1/R1_Qwen1.5B_0.001_10_Hard
2B • Updated • 1
a-F1/R1_Qwen7B_0.001_10_Hard
Updated
a-F1/R1_Qwen1.5B_0.001_10_Mid
2B • Updated • 2
a-F1/R1_Qwen7B_0.001_10_Mid
Updated
a-F1/R1_Qwen1.5B_0.001_10_easy
2B • Updated • 1