Search

Jincheng YU

DC-Gen: Post-Training Diffusion Acceleration with Deeply Compressed Latent Space
DC-VideoGen: Efficient Video Generation with Deep Compression Video Autoencoder
SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer
DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer
3 Papers accepted by ICCV 2025. 🎉🎉🎉
SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation
4 Papers accepted by ICML 2025. 🎉🎉🎉
SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer
8 Papers accepted by ICLR 2025. 🎉🎉🎉

Published with Hugo Blox Builder — the free, open source website builder that empowers creators.