Yutong Feng

6

Papers

121

Total Citations

Papers (6)

Ranni: Taming Text-to-Image Diffusion for Accurate Instruction Following

Learning Disentangled Identifiers for Action-Customized Text-to-Image Generation

Mimir: Improving Video Diffusion Models for Precise Text Understanding

ROSE: Remove Objects with Side Effects in Videos

Check Locate Rectify: A Training-Free Layout Calibration System for Text-to-Image Generation

Troika: Multi-Path Cross-Modal Traction for Compositional Zero-Shot Learning