3 papers
cs.CV2026
SparkDiffusion: Mitigating the High-Sparsity Trap --- A Unified Framework for up to Single-GPU Acceleration of Visual Generation
Yuxi Liu, Haoyu Li, Zekun Zhang +12
Video diffusion transformers are expensive because attention dominates long spatiotemporal token sequences. We identify the \emph{high-sparsity trap}: at extreme attention sparsity…
cs.CV2026
1.x-Distill: Breaking the Diversity, Quality, and Efficiency Barrier in Distribution Matching Distillation
Haoyu Li, Tingyan Wen, Lin Qi +6
Diffusion models produce high-quality text-to-image results, but their iterative denoising is computationally expensive.Distribution Matching Distillation (DMD) emerges as a promis…
cs.CV2024
MambaSCI: Efficient Mamba-UNet for Quad-Bayer Patterned Video Snapshot Compressive Imaging
Zhenghao Pan, Haijin Zeng, Jiezhang Cao +3
Color video snapshot compressive imaging (SCI) employs computational imaging techniques to capture multiple sequential video frames in a single Bayer-patterned measurement. With th…