10 papers
VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization
Junhao Cheng, Liang Hou, Tianxiong Zhong +4
The recent "Reasoning with Video" paradigm utilizes Video Generation Models (VGMs) to generate temporally coherent visual trajectories to complete reasoning tasks. Although state-o…
Stable Velocity: A Variance Perspective on Flow Matching
Donglin Yang, Yongxing Zhang, Xin Yu +5
While flow matching is elegant, its reliance on single-sample conditional velocities leads to high-variance training targets that destabilize optimization and slow convergence. By…
SURF: Signature-Retained Fast Video Generation
Kaixin Ding, Xi Chen, Sihui Ji +4
The demand for high-resolution video generation is growing rapidly. However, the generation resolution is severely constrained by slow inference speeds. For instance, Wan2.1 requir…
RectifiedHR: Enable Efficient High-Resolution Synthesis via Energy Rectification
Zhen Yang, Guibao Shen, Minyang Li +5
Diffusion models have achieved remarkable progress across various visual generation tasks. However, their performance significantly declines when generating content at resolutions…
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…
Boosting Resolution Generalization of Diffusion Transformers with Randomized Positional Encodings
Liang Hou, Cong Liu, Mingwu Zheng +4
Resolution generalization in image generation tasks enables the production of higher-resolution images with lower training resolution overhead. However, a key obstacle for diffusio…