Posts

Publication Dec 10, 2025

Bidirectional Normalizing Flow: From Data to Noise and Back

publication vision image

Submitted to CVPR 2026

Y. Lu, Q. Sun, X. Wang*, Z. Jiang, H. Zhao, K. He

Details •arXiv

Publication Sep 25, 2025

SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer

publication vision video

Submitted to ICLR 2026

J. Chen, Y. Zhao, J. Yu*, R. Chu, J. Chen, S. Yang, X. Wang, Y. Pan, D. Zhou, H. Ling, H. Liu, H. Yi, H. Zhang, M. Li, Y. Chen, H. Cai, S. Fidler, P. Luo, S. Han, E. Xie

Details •arXiv

Publication Sep 22, 2025

LongLive: Real-time Interactive Long Video Generation

publication vision video

Submitted to ICLR 2026

S. Yang, W. Huang, R. Chu, Y. Xiao, Y. Zhao, X. Wang, M. Li, E. Xie, Y. Chen, Y. Lu, S. Han, Y. Chen

Details •arXiv

Publication May 20, 2025

H3DP: Triply-Hierarchical Diffusion Policy for Visuomotor Learning

publication robotics

Submitted to ICLR 2026

Y. Lu, Y. Tian, Z. Yuan*, X. Wang, P. Hua, Z. Xue, H. Xu

Details •arXiv

Blog Jan 15, 2025

Deep Learning Review Session

blog notes

A concise summary of deep learning concepts and models.

NOTE: This blog is not finished.