AI Paper Atlas

Research map / Video / Video generation

SwiftVideo: A Unified Framework for Few-Step Video Generation Through Trajectory-Distribution Alignment

Yanxiao Sun, Jiafu Wu, Yun Cao, Chengming Xu, Yabiao Wang, Weijian Cao, Donghao Luo, Chengjie Wang, Yanwei Fu

AAAI 2026 · Video › Video generation · approach: Efficient video diffusion models · 9 citations (OpenAlex)

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 distribution alignment to CCD (ablation)SwiftVideo · OpenVid-1M test, 4 stepsFVD: 172.54 -> 136.14Improved
use continuous-time instead of discrete-time consistency distillation before DA (ablation)SwiftVideo · OpenVid-1M test, 4 stepsFVD: 151.23 -> 136.14Improved
add consistency distillation (CCD) before DA (ablation)SwiftVideo · OpenVid-1M test, 4 stepsFVD: 163.54 -> 136.14Improved
add trajectory alignment (DPO with synthetic step preferences) (ablation)SwiftVideo · OpenVid-1M test, 4 stepsFVD: 136.14 -> 118.89Improved
use lognorm(-0.6,1.4) instead of uniform(0,1) timestep sampler (ablation)SwiftVideo · OpenVid-1M test, 4 stepsFVD: 140.36 -> 136.14Improved
use lognorm(-0.6,1.4) instead of lognorm(-0.8,1.0) timestep sampler (ablation)SwiftVideo · OpenVid-1M test, 4 stepsFVD: 138.5 -> 136.14Improved
use synthetic preference pairs from different step counts instead of real data as preferred samples (ablation)trajectory alignment · OpenVid-1MFVD trendImproved
add reflow loss regularization to DPO (ablation)trajectory alignment · OpenVid-1MWin Diff stability / peak performanceImproved
vary lambda_RF among 1, 2, 3 (ablation)trajectory alignment · OpenVid-1Mtraining convergenceNo clear effect
use tangent normalization instead of tangent clipping (ablation)CCD · OpenVid-1MqualityImproved
use SwiftVideo (4 steps) instead of DMD2 (4 steps)DMD2 · OpenVid-1M testFVD: 167.42 -> 118.89Improved
use SwiftVideo (4 steps) instead of teacher with 4 stepsWan2.1 teacher · OpenVid-1M testFVD: 321.95 -> 118.89Improved

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