Youpeng Li

Leopo1d's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper about 1 month ago

From SFT to RL: Demystifying the Post-Training Pipeline for LLM-based Vulnerability Detection

Paper • 2602.14012 • Published Feb 15 • 1

updated a collection about 1 month ago

OpenVul

Collection

Datasets and Model Checkpoints for Paper "From SFT to RL: Demystifying the Post-Training Pipeline for LLM-based Vulnerability Detection" • 16 items • Updated Feb 17

updated 6 models about 1 month ago

Leopo1d/OpenVul-Qwen3-4B-GRPO

Text Generation • 196k • Updated Feb 17 • 15

Leopo1d/OpenVul-Qwen3-4B-DPO

Text Generation • 4B • Updated Feb 17 • 2

Leopo1d/OpenVul-Qwen3-4B-ORPO

Text Generation • 4B • Updated Feb 17 • 3

Leopo1d/OpenVul-Qwen3-4B-SFT-ep3

Text Generation • 196k • Updated Feb 17 • 440

Leopo1d/OpenVul-Qwen3-4B-SFT-ep1

Text Generation • 196k • Updated Feb 17 • 2

Leopo1d/OpenVul-Qwen3-4B-SFT-ep5

Text Generation • 196k • Updated Feb 17 • 4

updated 9 datasets about 1 month ago

Leopo1d/OpenVul_Sample_Specification_for_RL_Reward_Evaluation

Viewer • Updated Feb 15 • 15.6k • 30

Leopo1d/OpenVul_CWE_Hierarchical_Mapping

Viewer • Updated Feb 15 • 944 • 30 • 1

Leopo1d/OpenVul_Ground_Truth_Vulnerability_Information

Viewer • Updated Feb 15 • 9.77k • 31

Leopo1d/OpenVul_Vulnerability_Query_Dataset_for_RL

Viewer • Updated Feb 15 • 19.5k • 45

Leopo1d/OpenVul_Vulnerability_Preference_Dataset_for_DPO

Viewer • Updated Feb 15 • 7.24k • 16

Leopo1d/OpenVul_Vulnerability_Preference_Dataset_for_ORPO

Viewer • Updated Feb 15 • 7.05k • 17

Leopo1d/OpenVul_Rationalization_based_Vulnerability_Reasoning_Dataset_for_SFT

Viewer • Updated Feb 15 • 15.6k • 19

Leopo1d/OpenVul_Rejection_Sampling_based_Vulnerability_Reasoning_Dataset_for_SFT

Viewer • Updated Feb 15 • 6.28k • 24 • 1

Leopo1d/OpenVul_Distilled_Vulnerability_Reasoning_CoTs_from_DeepSeek-R1-0528

Viewer • Updated Feb 15 • 15.6k • 27

updated a collection about 1 month ago

OpenVul

Collection

Datasets and Model Checkpoints for Paper "From SFT to RL: Demystifying the Post-Training Pipeline for LLM-based Vulnerability Detection" • 16 items • Updated Feb 17