Ziyu Wang

8

Papers

32

Total Citations

Papers (8)

Whole-Song Hierarchical Generation of Symbolic Music Using Cascaded Diffusion Models

Distill Gold from Massive Ores: Bi-level Data Pruning towards Efficient Dataset Distillation

Dancing with Still Images: Video Distillation via Static-Dynamic Disentanglement

Efficient Fine-Grained Guidance for Diffusion Model Based Symbolic Music Generation

Unsupervised Disentanglement of Content and Style via Variance-Invariance Constraints

On Probabilistic Truncation in Privacy-preserving Machine Learning

Synthetic Video Enhances Physical Fidelity in Video Synthesis

Is In-Context Learning in Large Language Models Bayesian? A Martingale Perspective