safety-alignment

1 个项目 · ⭐ 12

ChanLiang/VAA

[ICML 2025] Vulnerability-Aware Alignment: Mitigating Uneven Forgetting in Harmful Fine-Tuning

Python ⭐ 12 ⑂ 0 · 2025-06-11推送

ai-safety fine-tuning

2025-06-11