QiMeng-PRepair: Precise Code Repair via Edit-Aware Reward Optimization
Changxin Ke
kcxain
AI & ML interests
NLPer
Organizations
None yet
QiMeng-MuPa: Mutual-Supervised Learning for Sequential-to-Parallel Code Translation
-
QiMeng-MuPa: Mutual-Supervised Learning for Sequential-to-Parallel Code Translation
Paper • 2506.11153 • Published -
kcxain/BabelTower
Viewer • Updated • 233 • 13 • 3 -
kcxain/translator-Qwen3-0.6B
Text Generation • 0.6B • Updated • 8 • 1 -
kcxain/translator-Qwen2.5-Coder-7B
Text Generation • 8B • Updated • 6
QiMeng-PRepair: Precise Code Repair via Edit-Aware Reward Optimization
QiMeng-MuPa: Mutual-Supervised Learning for Sequential-to-Parallel Code Translation
-
QiMeng-MuPa: Mutual-Supervised Learning for Sequential-to-Parallel Code Translation
Paper • 2506.11153 • Published -
kcxain/BabelTower
Viewer • Updated • 233 • 13 • 3 -
kcxain/translator-Qwen3-0.6B
Text Generation • 0.6B • Updated • 8 • 1 -
kcxain/translator-Qwen2.5-Coder-7B
Text Generation • 8B • Updated • 6
models 9
kcxain/Prepair-Verilog-3B-EA
Updated • 1
kcxain/Prepair-Python-7B-GRPO
8B • Updated • 2
kcxain/Prepair-Verilog-7B-GRPO
8B • Updated • 3
kcxain/Qwen3.5-4B-CC
504k • Updated • 1
kcxain/Prepair-Verilog-7B-EA
8B • Updated • 4
kcxain/Prepair-Python-7B-EA
8B • Updated • 3
kcxain/translator-Llama-3-8B
Text Generation • 8B • Updated • 6
kcxain/translator-Qwen2.5-Coder-7B
Text Generation • 8B • Updated • 6
kcxain/translator-Qwen3-0.6B
Text Generation • 0.6B • Updated • 8 • 1