AI Paper Atlas

Research map / Video / Video generation

RAPID: Reusing Attention Sparsity with Inter-step Adaptation for Efficient Video Diffusion

Shangran Lin, Lu Lu, Jian Chen, Qiang Liu

CVPR 2026 · Video › Video generation · approach: Efficient video diffusion models

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add Top-K anchor to Top-p block selection (hybrid vs Top-p only) (ablation)RAPID · Wan2.1-14B, density 39.2%PSNR: 18.922 -> 25.897Improved
add Top-p expansion to Top-K block selection (hybrid vs Top-K only) (ablation)RAPID · Wan2.1-14B, density 39.2%PSNR: 25.487 -> 25.897Improved
add Top-p expansion to Top-K block selection (hybrid vs Top-K only) (ablation)RAPID · Wan2.1-14B, density 54.4%PSNR: 27.377 -> 28.176Improved
extend dense warm-up from 25% to 40% of steps (ablation)RAPID · Wan2.1-14BPSNR/qualityNo clear effect
lengthen dense warm-up from 5% to 25% of steps (ablation)RAPID · Wan2.1-14Bgeneration qualityImproved
raise Top-p threshold tau from 0.5 to 0.9 (k_min fixed at 10%) (ablation)RAPID · Wan2.1-14B, Tw=25%generation qualityImproved
reuse one-shot cached mask instead of per-step dynamic masks, at matched density (RAPID vs Radial Attn)Wan2.1-14B · VBench-2.0 prompts (768P, 81 frames)PSNR: 22.916 -> 26.112Improved
reuse one-shot cached mask on HunyuanVideo (RAPID vs Radial Attn)HunyuanVideo · VBench-2.0 prompts (768P, 129 frames)PSNR: 27.499 -> 31.488Improved
add Turbo mode: re-threshold cached scores for more aggressive mask in later stepsRAPID · Wan2.1-14Bspeedup / PSNR: 1.53x -> 1.79x speedup; 26.112 -> 22.612 PSNRMixed
add Turbo mode to RAPID on HunyuanVideoRAPID · HunyuanVideospeedup / PSNR: 1.73x -> 2.01x speedup; 31.488 -> 26.786 PSNRMixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy