2 papers
cs.CV2026
VMonarch: Efficient Video Diffusion Transformers with Structured Attention
Cheng Liang, Haoxian Chen, Liang Hou +4
The quadratic complexity of the attention mechanism severely limits the context scalability of Video Diffusion Transformers (DiTs). We find that the highly sparse spatio-temporal a…
cs.CV2025
VideoMAP: Toward Scalable Mamba-based Video Autoregressive Pretraining
Yunze Liu, Peiran Wu, Cheng Liang +3
Recent Mamba-based architectures for video understanding demonstrate promising computational efficiency and competitive performance, yet struggle with overfitting issues that hinde…