From SFT to RL: Demystifying the Post-Training Pipeline for LLM-based Vulnerability Detection
Paper
• 2602.14012 • Published
• 1
Youpeng Li
Leopo1d
AI & ML interests
None yet
Recent Activity
View all activity
Organizations
None yet
upvoted a paper 6 days ago
updated a collection 9 days ago
updated 6 models 9 days ago
Leopo1d/OpenVul-Qwen3-4B-GRPO
Text Generation • 196k • Updated
• 20
Leopo1d/OpenVul-Qwen3-4B-DPO
Text Generation • 4B • Updated
• 16
Leopo1d/OpenVul-Qwen3-4B-ORPO
Text Generation • 4B • Updated
• 19
Leopo1d/OpenVul-Qwen3-4B-SFT-ep3
Text Generation • 196k • Updated
• 348
Leopo1d/OpenVul-Qwen3-4B-SFT-ep1
Text Generation • 196k • Updated
• 22
Leopo1d/OpenVul-Qwen3-4B-SFT-ep5
Text Generation • 196k • Updated
• 83
updated 9 datasets 11 days ago
Leopo1d/OpenVul_Sample_Specification_for_RL_Reward_Evaluation
Viewer
• Updated
• 15.6k • 27
Leopo1d/OpenVul_CWE_Hierarchical_Mapping
Viewer
• Updated
• 944 • 20
Leopo1d/OpenVul_Ground_Truth_Vulnerability_Information
Viewer
• Updated
• 9.77k • 26
Leopo1d/OpenVul_Vulnerability_Query_Dataset_for_RL
Viewer
• Updated
• 19.5k • 28
Leopo1d/OpenVul_Vulnerability_Preference_Dataset_for_DPO
Viewer
• Updated
• 7.24k • 20
Leopo1d/OpenVul_Vulnerability_Preference_Dataset_for_ORPO
Viewer
• Updated
• 7.05k • 16
Leopo1d/OpenVul_Rationalization_based_Vulnerability_Reasoning_Dataset_for_SFT
Viewer
• Updated
• 15.6k • 13
Leopo1d/OpenVul_Rejection_Sampling_based_Vulnerability_Reasoning_Dataset_for_SFT
Viewer
• Updated
• 6.28k • 14
Leopo1d/OpenVul_Distilled_Vulnerability_Reasoning_CoTs_from_DeepSeek-R1-0528
Viewer
• Updated
• 15.6k • 14
updated a collection 11 days ago