PUMA: Empowering Unified MLLM with Multi-Granular Visual Generation

Rongyao Fang, Chengqi Duan, Kun Wang, Hao Li 0069, Linjiang Huang, Hao Tian 0006, Xingyu Zeng, Rui Zhao 0001, Jifeng Dai, Hongsheng Li 0001, Xihui Liu. PUMA: Empowering Unified MLLM with Multi-Granular Visual Generation. In IEEE/CVF International Conference on Computer Vision, ICCV 2025, Honolulu, HI, USA, October 19-25, 2025. pages 15447-15457, IEEE, 2025. [doi]

Abstract

Abstract is missing.