Large Reward Models: Generalizable Online Robot Reward Generation with Vision-Language Models

Recommended citation: @misc{tri_lrm, title={Large Reward Models: Generalizable Online Robot Reward Generation with Vision-Language Models}, author={Yanru Wu and Weiduo Yuan and Ang Qi and Vitor Guizilini and Jiageng Mao and Yue Wang}, year={2026}, eprint={2603.16065}, archivePrefix={arXiv}, primaryClass={cs.RO}, url={https://arxiv.org/abs/2603.16065}, }