AI Paper Atlas

Research map / Video / Video generation

SALT: Self-Consistent Distribution Matching with Cache-Aware Training for Few-Step Video Generation

Xingtong Ge, Yi ZHANG, Yushi Huang, Dailan He, Xiahong Wang, Bingqi Ma, Guanglu Song, Yu Liu, Jun Zhang

ECCV 2026 · Video › Video generation · approach: Autoregressive long video generation

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 self-consistency loss on top of denser 8-point grid DMD (ablation)DMD-8 · Wan2.1 T2V 1.3B VBench (4 NFE)Total Score: 82.54 -> 83.36Improved
train DMD on denser 8-point grid instead of 4-point grid (ablation)DMD-4 · Wan2.1 T2V 1.3B VBench (4 NFE)Total Score: 82.78 -> 82.54Hurt
add mixed-step rollout when using SC loss (ablation)Causal Forcing + L_SC · VBench AR (Causal Forcing, 4 NFE)Total Score: 83.83 -> 85.02Improved
add naive SC loss to official baseline without mixed-step (ablation)Causal Forcing · VBench AR (Causal Forcing, 4 NFE)Total Score: 84.62 -> 83.83Hurt
add cache-conditioned reference alignment (ablation)Causal Forcing + mixed-step + L_SC · VBench AR (Causal Forcing, 4 NFE)Total Score: 85.02 -> 85.08Improved
add cache-conditioned reference alignment (ablation)Causal Forcing + mixed-step + L_SC · VBench AR (Causal Forcing, 2 NFE)Semantic Score: 80.65 -> 81.49Improved
add SC-DMD regularization to DMD (ablation)DMD · VBench-I2V Wan2.1 14B (4 NFE)Temporal Flickering: 95.21 -> 97.41Improved
add SC-DMD regularization to DMDDMD · VBench-I2V Wan2.1 14B (4 NFE)Dynamic Degree: 58.46 -> 52.85Hurt
add Salt training to Causal ForcingCausal Forcing · VBench-Long 30-secondDynamic Degree: 76.95 -> 54.02Hurt
add Salt training to Causal ForcingCausal Forcing · VBench 5-second (4 NFE)Total Score: 84.62 -> 85.08Improved
add Salt training to LongLiveLongLive · VBench 5-second (4 NFE)Total Score: 84.40 -> 84.93Improved
hybrid DMD with shortcut flow matching loss on mismatched grid (ablation)DMD · Wan2.1 T2V 1.3B VBench (4 NFE)Total Score: 82.78 -> 75.06Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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