3 papers
cs.CV2025
Compact Attention: Exploiting Structured Spatio-Temporal Sparsity for Fast Video Generation
Qirui Li, Guangcong Zheng, Qi Zhao +4
The computational demands of self-attention mechanisms pose a critical challenge for transformer-based video generation, particularly in synthesizing ultra-long sequences. Current…
cs.CV2025
RainFusion: Adaptive Video Generation Acceleration via Multi-Dimensional Visual Redundancy
Aiyue Chen, Bin Dong, Jingru Li +4
Video generation using diffusion models is highly computationally intensive, with 3D attention in Diffusion Transformer (DiT) models accounting for over 80\% of the total computati…
math.AG2023
Machine learning assisted exploration for affine Deligne-Lusztig varieties
Bin Dong, Xuhua He, Pengfei Jin +2
This paper presents a novel, interdisciplinary study that leverages a Machine Learning (ML) assisted framework to explore the geometry of affine Deligne-Lusztig varieties (ADLV). T…