[1]
Zeng, X. et al. 2026. FDC-Ground: Improving GRPO for GUI Grounding via Exponential Rewards and Fact-Aligned Pruning. Proceedings of the AAAI Conference on Artificial Intelligence. 40, 33 (Mar. 2026), 28122–28130. DOI:https://doi.org/10.1609/aaai.v40i33.40038.