Yan Kang

6

Papers

40

Total Citations

Papers (6)

Attention-Driven Training-Free Efficiency Enhancement of Diffusion Models

Mixture of Efficient Diffusion Experts Through Automatic Interval and Sub-Network Selection

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers

DOLLAR: Few-Step Video Generation via Distillation and Latent Reward Optimization

Generating, Fast and Slow: Scalable Parallel Video Generation with Video Interface Networks

SNED: Superposition Network Architecture Search for Efficient Video Diffusion Model