Taiwen He

2
Papers
398
Total Citations

Papers (2)

RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback

CVPR 2024
344
citations

RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness

CVPR 2025
54
citations