Jiayi Zhou
Ph.D Student
Ph.D (2024), Peking University
Interests
- Reinforcement Learning
- AI Safety
- Preference Modeling
Latest
- AI Alignment: A Comprehensive Survey
- Safe RLHF-V: Safe Reinforcement Learning from Multi-modal Human Feedback
- Generative RLHF-V: Learning Principles from Multi-modal Human Preference
- InterMT: Multi-Turn Interleaved Preference Alignment with Human Feedback
- Reward Generalization in RLHF: A Topological Perspective
- Sequence to Sequence Reward Modeling: Improving RLHF by Language Feedback
- Align Anything: Training All-Modality Models to Follow Instructions with Language Feedback
- OmniSafe: An Infrastructure for Accelerating Safe Reinforcement Learning Research
- Language Models Resist Alignment: Evidence From Data Compression
- Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmark