6 papers · 1 filter
MC-Sparse: Deconstructing and Closing the Dense-Sparse Attention Gap in Diffusion Transformers
Jiarui Chen, Zeqiang Lai, Jiangshan Wang +5
Sparse attention is a primary approach to reducing the latency of diffusion transformers in long-sequence generation tasks, such as video and high-resolution 3D asset generation. H…
PreciseCache: Precise Feature Caching for Efficient and High-fidelity Video Generation
Jiangshan Wang, Kang Zhao, Jiayi Guo +5
High computational costs and slow inference hinder the practical application of video generation models. While prior works accelerate the generation process through feature caching…
Elastic Diffusion Transformer
Jiangshan Wang, Zeqiang Lai, Jiarui Chen +5
Diffusion Transformers (DiT) have demonstrated remarkable generative capabilities but remain highly computationally expensive. Previous acceleration methods, such as pruning and di…
Efficient Autoregressive Video Diffusion with Dummy Head
Hang Guo, Zhaoyang Jia, Jiahao Li +5
The autoregressive video diffusion model has recently gained considerable research interest due to its causal modeling and iterative denoising. In this work, we identify that the m…
MultiMotion: Multi Subject Video Motion Transfer via Video Diffusion Transformer
Penghui Liu, Jiangshan Wang, Yutong Shen +3
Multi-object video motion transfer poses significant challenges for Diffusion Transformer (DiT) architectures due to inherent motion entanglement and lack of object-level control.…
FastVAR: Linear Visual Autoregressive Modeling via Cached Token Pruning
Hang Guo, Yawei Li, Taolin Zhang +4
Visual Autoregressive (VAR) modeling has gained popularity for its shift towards next-scale prediction. However, existing VAR paradigms process the entire token map at each scale s…