CrowdVLM-R1: Expanding R1 Ability to Vision Language Model for Crowd Counting using Fuzzy Group Relative Policy Reward

Zhiqiang Wang, Pengbin Feng, YanBin Lin, Shuzhang Cai, Zongao Bian, Jinghua Yan, Xingquan Zhu 0001. CrowdVLM-R1: Expanding R1 Ability to Vision Language Model for Crowd Counting using Fuzzy Group Relative Policy Reward. In IEEE International Conference on Big Data, BigData 2025, Macau, China, December 8-11, 2025. pages 1879-1886, IEEE, 2025. [doi]

Abstract

Abstract is missing.