← Search

Jingde Kong

2 accepted papers

2026

Plug-and-Play Fidelity Optimization for Diffusion Transformer Acceleration via Cumulative Error Minimization

ICLR 2026poster

Although Diffusion Transformer (DiT) has emerged as a predominant architecture for image and video generation, its iterative denoising process results in slow inference, which hinders broader applicability and development. Caching-based methods achieve training-free acceleration, while suffering fro…

Cited by 0SourcecodeScholar
2026

SODA: Sensitivity-Oriented Dynamic Acceleration for Diffusion Transformer

CVPR 2026

Diffusion Transformers have become a dominant paradigm in visual generation, yet their low inference efficiency remains a key bottleneck hindering further advancement. Among common training-free techniques, caching offers high acceleration efficiency but often compromises fidelity, whereas pruning s

Cited by 0SourcecodeScholar