Yijun Li

11

Papers

152

Total Citations

Papers (11)

UniReal: Universal Image Generation and Editing via Learning Real-world Dynamics

Attention-Driven Training-Free Efficiency Enhancement of Diffusion Models

Generative Video Propagation

Generative Image Layer Decomposition with Visual Effects

X-Fusion: Introducing New Modality to Frozen Large Language Models

Removing Distributional Discrepancies in Captions Improves Image-Text Alignment

MAGICK: A Large-scale Captioned Dataset from Matting Generated Images using Chroma Keying

Scene Graph Guided Generation: Enable Accurate Relations Generation in Text-to-Image Models via Textural Rectification

Distributionally Robust Policy Evaluation and Learning for Continuous Treatment with Observational Data

The Causal Impact of Credit Lines on Spending Distributions

TransPixeler: Advancing Text-to-Video Generation with Transparency