@misc{ong2025vlprms,
title={Training Vision-Language Process Reward Models for Test-Time Scaling in Multimodal Reasoning: Key Insights and Lessons Learned},
author={Brandon Ong, Tej Deep Pala, Vernon Toh, William Chandra Tjhi, and Soujanya Poria},
year={2025},
eprint={2509.23250},
archivePrefix={arXiv},
primaryClass={cs.AI},
url={https://arxiv.org/pdf/2509.23250},
}
@misc{ong2025vlprms,
title={Training Vision-Language Process Reward Models for Test-Time Scaling in Multimodal Reasoning: Key Insights and Lessons Learned},
author={Brandon Ong, Tej Deep Pala, Vernon Toh, William Chandra Tjhi, and Soujanya Poria},
year={2025},
eprint={2509.23250},
archivePrefix={arXiv},
primaryClass={cs.AI},
url={https://arxiv.org/pdf/2509.23250},
}