Songwei Ge

3
Papers
161
Total Citations

Papers (3)

Grounded Text-to-Image Synthesis with Attention Refocusing

CVPR 2024
157
citations

A Comprehensive Study of Decoder-Only LLMs for Text-to-Image Generation

CVPR 2025
4
citations

On the Content Bias in Fréchet Video Distance

CVPR 2024
0
citations