新方法提高了AI图像和视频生成的效率

报道来源 [4]

1. arXiv cs.CV TIER_1 Italiano(IT) · Xinchao Wang · 2026-05-20 11:58

   Q-ARVD: Quantizing Autoregressive Video Diffusion Models

   Autoregressive video diffusion models (ARVDs) have emerged as a promising architecture for streaming video generation, paving the way for real-time interactive video generation and world modeling. Despite their potential, the substantial inference cost of ARVDs remains a major ob…

2. arXiv cs.CV TIER_1 English(EN) · Gordon Wetzstein · 2026-05-18 17:55

   Spectral Progressive Diffusion for Efficient Image and Video Generation

   Diffusion models have been shown to implicitly generate visual content autoregressively in the frequency domain, where low-frequency components are generated earlier in the denoising process while high-frequency details emerge only in later timesteps. This structure offers a natu…

3. arXiv cs.CV TIER_1 English(EN) · Linfeng Zhang · 2026-05-18 12:58

   Focused Forcing: Content-Aware Per-Frame KV Selection for Efficient Autoregressive Video Diffusion

   Recent advances in autoregressive video diffusion have enabled sequential and streaming video generation. However, long-horizon generation requires increasingly large KV caches, making efficient compression without sacrificing quality challenging. Existing methods mostly select h…

4. arXiv cs.CV TIER_1 English(EN) · Xulong Tang · 2026-05-18 04:18

   Temporal Aware Pruning for Efficient Diffusion-based Video Generation

   Video diffusion models have recently enabled high-quality video generation with ViT-based architectures, but remain computationally intensive because generation requires attention computation over long spatiotemporal sequences. Token pruning has proven effective for ViTs and VLMs…