Ziyu Wan
2 indexed papers
Recent (6 mo)
2With code
0Influential cites
0Benchmarked
0Publications per year
226
Top categories
Sound×1Vision×1
Frequent co-authors
Research Timeline
2026
OPSD-V: On-Policy Self-Distillation for Post-Training Few-Step Autoregressive Video Generators
This paper proposes OPSD-V, an on-policy self-distillation method for reducing long-horizon degradation in few-step autoregressive video diffusion models by introducing real long-video data as temporal context during training.
Music-JEPA: Learning a World Model of Sound from Action
This paper proposes a method for learning a world model of piano sound using Joint Embedding Predictive Architectures (JEPA), treating music as an action-conditioned system.
Highlighted terms show continued research focus across papers