Yaofang Liu — accepted AI-conference papers

2026

Pusa V1.0: Unlocking Temporal Control in Pretrained Video Diffusion Models via Vectorized Timestep Adaptation

Yaofang Liu, Yumeng REN, Aitor Artola, Yuxuan Hu, Xiaodong Cun, Xiaotong Zhao +6

ICLR 2026poster

The rapid advancement of video diffusion models has been hindered by fundamental limitations in temporal modeling, particularly the rigid synchronization of frame evolution imposed by conventional scalar timestep variables. While task-specific adaptations and autoregressive models have sought to add…

Cited by 0 Source ↗code ↗Scholar ↗

2024

EvalCrafter: Benchmarking and Evaluating Large Video Generation Models

Yaofang Liu, Xiaodong Cun, Xuebo Liu, Xintao Wang, Yong Zhang, Haoxin Chen +4

CVPR 2024poster

The vision and language generative models have been overgrown in recent years. For video generation various open-sourced models and public-available services have been developed to generate high-quality videos. However these methods often use a few metrics e.g. FVD or IS to evaluate the performance.…

Cited by 126 Source ↗PDF ↗code ↗Scholar ↗