PKU-Alignment ORG

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

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

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

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

Align Anything: Training All-modality Model with Feedback

[NeurIPS 2024 Oral] Aligner: Efficient Alignment by Learning to Correct

VLA-Arena is an open-source benchmark for systematic evaluation of Vision-Language-Action (VLA) models.

BeaverTails is a collection of datasets designed to facilitate research on safety alignment in large language models (LLMs).

[NeurIPS 2025 Spotlight] Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning.

AI Alignment: A Comprehensive Survey

ICLR 2024: SafeDreamer: Safe Reinforcement Learning with World Models

AAAI24(Oral) ProAgent: Building Proactive Cooperative Agents with Large Language Models

[ACL2025 Best Paper] Language Models Resist Alignment

SafeSora is a human preference dataset designed to support safety alignment research in the text-to-video generation field, aiming to enhance the helpfulness and harmlessness of Large Vision Models (LVMs).

ReDMan is an open-source simulation platform that provides a standardized implementation of safe RL algorithms for Reliable Dexterous Manipulation.

Alignment with a millennium of moral progress. Spotlight@NeurIPS 2024 Track on Datasets and Benchmarks.

No description.

[ICML 2025 Poster] SAE-V: Interpreting Multimodal Models for Enhanced Alignment

No description.

No description.

S1-M: Simple Test-time Scaling in Multimodal Reasoning

No description.

No description.

No description.

No description.