GeezerVison

GeezerVison is showing github.com — PKU-Alignment

README.md

PKU-Alignment Team

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

omnisafe omnisafe Public

JMLR: OmniSafe is an infrastructural framework for accelerating SafeRL research.

Python 1.2k 161
safety-gymnasium safety-gymnasium Public

NeurIPS 2023: Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmark

Python 602 80
safe-rlhf safe-rlhf Public

Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback

Python 1.6k 135
Safe-Policy-Optimization Safe-Policy-Optimization Public

NeurIPS 2023: Safe Policy Optimization: A benchmark repository for safe reinforcement learning algorithms

Python 427 61

Repositories

Type

All Public Sources Forks Archived Mirrors Templates

Language

All HTML JavaScript Makefile Python

Sort

Last updated Name Stars

Showing 10 of 26 repositories

SPIKE-Bench Public

PKU-Alignment/SPIKE-Bench's past year of commit activity

Python 3 Apache-2.0 0 0 0 Updated Aug 1, 2026
safety-gymnasium Public
NeurIPS 2023: Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmark

PKU-Alignment/safety-gymnasium's past year of commit activity

Python 602 Apache-2.0 80 13 3 Updated Jul 21, 2026
VLA-Arena Public
VLA-Arena is an open-source benchmark for systematic evaluation of Vision-Language-Action (VLA) models.

PKU-Alignment/VLA-Arena's past year of commit activity

Python 222 Apache-2.0 18 1 2 Updated Jul 5, 2026
SafeVLA Public
[NeurIPS 2025 Spotlight] Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning.

PKU-Alignment/SafeVLA's past year of commit activity

Python 167 12 0 0 Updated Mar 31, 2026
align-anything Public
Align Anything: Training All-modality Model with Feedback

PKU-Alignment/align-anything's past year of commit activity

Python 4,669 Apache-2.0 503 28 3 Updated Nov 27, 2025
safe-rlhf Public
Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback

PKU-Alignment/safe-rlhf's past year of commit activity

Python 1,623 Apache-2.0 134 17 2 Updated Nov 24, 2025
MM-DeceptionBench Public

PKU-Alignment/MM-DeceptionBench's past year of commit activity

1 0 0 0 Updated Sep 25, 2025
eval-anything Public

PKU-Alignment/eval-anything's past year of commit activity

Python 23 Apache-2.0 17 1 2 Updated Jul 26, 2025
llms-resist-alignment Public
[ACL2025 Best Paper] Language Models Resist Alignment

PKU-Alignment/llms-resist-alignment's past year of commit activity

Python 54 1 1 0 Updated Jun 11, 2025
SAE-V Public
[ICML 2025 Poster] SAE-V: Interpreting Multimodal Models for Enhanced Alignment

PKU-Alignment/SAE-V's past year of commit activity

18 1 0 0 Updated Jun 5, 2025

View all repositories

People

Top languages

Python JavaScript Makefile HTML

Most used topics

reinforcement-learning rlhf safe-reinforcement-learning alignment llm