Jiaming Ji

5 papers Peking University

• Generative RLHF-V: Learning Principles from Multi-modal Human Preference
• InterMT: Multi-Turn Interleaved Preference Alignment with Human Feedback
• PHYBench: Holistic Evaluation of Physical Perception and Reasoning in Large Language Models
• Safe RLHF-V: Safe Reinforcement Learning from Multi-modal Human Feedback
• SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning