Recent advances in fine-tuning multimodal large language models (MLLMs) using reinforcement learning have achieved remarkable progress, particularly with the introduction of various entropy control techniques. However, the role and characteristics of entropy in perception-oriented tasks like visual grounding, as well as effective strategies for controlling it, remain largely unexplored. To address this issue, we focus on the visual grounding task and analyze the role and characteristics of entropy in comparison to reasoning tasks. Building on these findings, we introduce ECVGPO (Entropy Control Visual Grounding Policy Optimization), an interpretable algorithm designed for effective entropy regulation. Through entropy control, the trade-off between exploration and exploitation is better balanced. Experiments show that ECVGPO achieves broad improvements across various benchmarks and models.
@article{arxiv.2512.06726,
title = {The Role of Entropy in Visual Grounding: Analysis and Optimization},
author = {Shuo Li and Jiajun Sun and Zhihao Zhang and Xiaoran Fan and Senjie Jin and Hui Li and Yuming Yang and Junjie Ye and Lixing Shen and Tao Ji and Tao Gui and Qi Zhang and Xuanjing Huang},
journal= {arXiv preprint arXiv:2512.06726},
year = {2025}
}