Yaodong Yang
20 papers · 1415 citations
Most-cited papers
- Safe RLHF: Safe Reinforcement Learning From Human Feedback2023 · 645 citations
- JARVIS-1: Open-world Multi-task Agents With Memory-augmented Multimodal Language Models2023 · 177 citations
- Pku-saferlhf: Towards Multi-level Safety Alignment For Llms With Human Preference2024 · 163 citations
- Proagent: Building Proactive Cooperative Agents With Large Language Models2023 · 140 citations
- Aligner: Efficient Alignment By Learning To Correct2024 · 87 citations
- Theoretically Guaranteed Policy Improvement Distilled From Model-based Planning2023 · 1 citations
- Model Evolution Framework With Genetic Algorithm For Multi-task Reinforcement Learning2025
- Towards Efficient Collaboration Via Graph Modeling In Reinforcement Learning2024
Topics