Change the repository type filter
All
Repositories list
14 repositories
- JMLR: OmniSafe is an infrastructural framework for accelerating SafeRL research.
align-anything
PublicAlign Anything: Training All-modality Model with Feedbacksafe-sora
PublicSafeSora 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).safe-rlhf
PublicSafe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedbackllms-resist-alignment
Public- NeurIPS 2023: Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmark
ProAgent
PublicProAgent: Building Proactive Cooperative Agents with Large Language ModelsSafeDreamer
PublicICLR 2024: SafeDreamer: Safe Reinforcement Learning with World Models- NeurIPS 2023: Safe Policy Optimization: A benchmark repository for safe reinforcement learning algorithms
AlignmentSurvey
PublicAI Alignment: A Comprehensive SurveyReDMan
Public