PKU-Alignment
Large language models (LLMs) have immense potential in the field of general intelligence but come with significant risks. As a research team at Peking University, we actively focus on alignment techniques for LLMs, such as safety alignment, to enhance the model's safety and reduce toxicity.
Welcome to follow our AI Safety project:
Pinned Loading
Repositories
- SPIKE-Bench Public
- safety-gymnasium Public
NeurIPS 2023: Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmark
- VLA-Arena Public
VLA-Arena is an open-source benchmark for systematic evaluation of Vision-Language-Action (VLA) models.
- SafeVLA Public
[NeurIPS 2025 Spotlight] Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning.
- safe-rlhf Public
Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback
- MM-DeceptionBench Public
- eval-anything Public
Top languages
Loading…
Most used topics
Loading…