4 papers
Accelerating Text-to-Video Generation with Calibrated Sparse Attention
Shai Yehezkel, Shahar Yadin, Noam Elata +2
Recent diffusion models enable high-quality video generation, but suffer from slow runtimes. The large transformer-based backbones used in these models are bottlenecked by spatiote…
Block Sparse Flash Attention
Daniel Ohayon, Itay Lamprecht, Itay Hubara +3
Modern large language models increasingly require long contexts for reasoning and multi-document tasks, but attention's quadratic complexity creates a severe computational bottlene…
InvFusion: Bridging Supervised and Zero-shot Diffusion for Inverse Problems
Noam Elata, Hyungjin Chung, Jong Chul Ye +2
Diffusion Models have demonstrated remarkable capabilities in handling inverse problems, offering high-quality posterior-sampling-based solutions. Despite significant advances, a f…
PSC: Posterior Sampling-Based Compression
Noam Elata, Tomer Michaeli, Michael Elad
Diffusion models have transformed the landscape of image generation and now show remarkable potential for image compression. Most of the recent diffusion-based compression methods…