Yujian Liu

5

Papers

16

Total Citations

Papers (5)

Correcting Diffusion Generation through Resampling

Fictitious Synthetic Data Can Improve LLM Factuality via Prerequisite Learning

Decomposing Uncertainty for Large Language Models through Input Clarification Ensembling

Uncovering the Disentanglement Capability in Text-to-Image Diffusion Models

Harnessing the Spatial-Temporal Attention of Diffusion Models for High-Fidelity Text-to-Image Synthesis