← authors · overview

• Safe RLHF: Safe Reinforcement Learning From Human Feedback
  2023 · 645 citations
• JARVIS-1: Open-world Multi-task Agents With Memory-augmented Multimodal Language Models
  2023 · 177 citations
• Pku-saferlhf: Towards Multi-level Safety Alignment For Llms With Human Preference
  2024 · 163 citations
• Proagent: Building Proactive Cooperative Agents With Large Language Models
  2023 · 140 citations
• Aligner: Efficient Alignment By Learning To Correct
  2024 · 87 citations
• Theoretically Guaranteed Policy Improvement Distilled From Model-based Planning
  2023 · 1 citations
• Towards Efficient Collaboration Via Graph Modeling In Reinforcement Learning
  2024
• Policy Improvement Reinforcement Learning
  2026
• Model Evolution Framework With Genetic Algorithm For Multi-task Reinforcement Learning
  2025