Datasets and Model Checkpoints for Paper "From SFT to RL: Demystifying the Post-Training Pipeline for LLM-based Vulnerability Detection"
Youpeng Li
Leopo1d
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 14 hours ago
From SFT to RL: Demystifying the Post-Training Pipeline for LLM-based Vulnerability Detection
updated
a collection
3 days ago
OpenVul
updated
a model
3 days ago
Leopo1d/OpenVul-Qwen3-4B-GRPO
Organizations
None yet