AI Paper Atlas

Research map / Video / Video generation

AAD-1: Asymmetric Adversarial Distillation for One-Step Autoregressive Video Generation

Haobo Li, Yanhong Zeng, Yunhong Lu, Jiapeng Zhu, Hao Ouyang, Qiuyu Wang, Ka Leong Cheng, Yujun Shen, Zhipeng Zhang

ICML 2026 · Video › Video generation · approach: Autoregressive long video generation · 0 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 DMD warmup before adversarial refinement (ablation)AAD-1 · VBench-I2VAesthetic Quality: 53.63 -> 58.64Improved
add DMD warmup before adversarial refinement (ablation)AAD-1 · VBench-I2VImaging Quality: 62.81 -> 69.37Improved
use bidirectional instead of causal discriminator backbone (video-wise logit) (ablation)AAD-1 discriminator · Drift Score (20s)Drift Score: 7.10 -> 4.02Improved
use video-wise instead of frame-wise logits on causal backbone (ablation)AAD-1 discriminator (causal) · VBench DynamicsDynamic Degree: 1.08 -> 42.07Improved
use video-wise instead of frame-wise logits on bidirectional backbone (ablation)AAD-1 discriminator (bidirectional) · Drift Score (20s)Drift Score: 4.38 -> 4.02Improved
use video-wise instead of frame-wise logits on bidirectional backbone (ablation)AAD-1 discriminator (bidirectional) · VBench DynamicsDynamic Degree: 39.04 -> 39.29No clear effect
Stage-III adversarial training over Stage-II DMD modelAAD-1 · VBench-I2VSubject Consistency: 92.14 -> 94.34Improved
Stage-III adversarial training over Stage-II DMD modelAAD-1 · VBench-I2VDynamic Degree: 50.30 -> 41.46Hurt
Stage-III adversarial training over Stage-II DMD modelAAD-1 · VBench-I2VI2V Subject: 96.56 -> 98.65Improved
raise sampling budget from 1 NFE to 2 NFEAAD-1 · VBench-I2V (480p, 5s)Dynamic Degree: 41.46 -> 50.04Improved
extend generation from 5s to 20sAAD-1 (1 NFE, 480p) · VBench-I2VSubject Consistency: 94.34 -> 84.31Hurt
use bidirectional instead of causal discriminator in Stage III training (ablation)AAD-1 · Training costtraining time: 65 hours -> 49 hoursImproved

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