 FreePCA: Integrating Consistency Information across Long-short Frames in Training-free Long Video Generation via Principal Component AnalysisComputer Vision and Pattern Recognition (CVPR), 2025 |
 Towards Precise Scaling Laws for Video Diffusion TransformersComputer Vision and Pattern Recognition (CVPR), 2024 |
 Grid Diffusion Models for Text-to-Video GenerationComputer Vision and Pattern Recognition (CVPR), 2024 |
 Sonic: Shifting Focus to Global Audio Perception in Portrait AnimationComputer Vision and Pattern Recognition (CVPR), 2024 |
 MovieBench: A Hierarchical Movie Level Dataset for Long Video GenerationComputer Vision and Pattern Recognition (CVPR), 2024 |
 ARLON: Boosting Diffusion Transformers with Autoregressive Models for Long Video GenerationInternational Conference on Learning Representations (ICLR), 2024 |
 LVCD: Reference-based Lineart Video Colorization with Diffusion ModelsACM Transactions on Graphics (TOG), 2024 |
