Xun Guo

6

Papers

522

Total Citations

Papers (6)

MovieChat: From Dense Token to Sparse Memory for Long Video Understanding

VideoWorld: Exploring Knowledge Learning from Unlabeled Videos

ARLON: Boosting Diffusion Transformers with Autoregressive Models for Long Video Generation

Noise-assisted Prompt Learning for Image Forgery Detection and Localization

I2VGuard: Safeguarding Images against Misuse in Diffusion-based Image-to-Video Models

Image as a World: Generating Interactive World from Single Image via Panoramic Video Generation