2025 Poster "reward function design" Papers
2 papers found
REvolve: Reward Evolution with Large Language Models using Human Feedback
RISHI HAZRA, Alkis Sygkounas, Andreas Persson et al.
ICLR 2025posterarXiv:2406.01309
8
citations
SC-Captioner: Improving Image Captioning with Self-Correction by Reinforcement Learning
Lin Zhang, Xianfang Zeng, Kangcong Li et al.
ICCV 2025posterarXiv:2508.06125
3
citations