AI Paper Atlas

Research map / Video / Video generation

Direct Autoregressive Diffusion Distillation via Error-aware Causal Pretraining

Jiaxing Li, Kaichen Huang, Baixin Xu, Zexiang Liu, Xianglong He, Zile Wang, Junyao Gao, Yang Liu, Ying He, Bo An, Yangguang Li

ECCV 2026 · Video › Video generation · approach: Efficient video diffusion models · 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
use Error Forcing instead of Teacher Forcing for pretraining (ablation)50-step causal model · VBenchVBench Total score: 79.15 -> 79.64Improved
use Error Forcing instead of Diffusion Forcing for pretraining (ablation)50-step causal model · VBenchVBench Total score: 78.22 -> 79.64Improved
initialize DMD from Error Forcing instead of Teacher Forcing (ablation)4-step student · VBenchVBench Total score: 80.77 -> 81.35Improved
initialize DMD from Error Forcing instead of Diffusion Forcing (ablation)4-step student · VBenchVBench Total score: 80.19 -> 81.35Improved
store errors frame-wise rather than chunk-wise (ablation)Error Forcing · VBenchVBench Total score: 79.08 -> 79.64Improved
store errors frame-wise rather than window-wise (ablation)Error Forcing · VBenchVBench Total score: 77.38 -> 79.64Improved
sample errors randomly rather than timestep-aware (ablation)Error Forcing · VBenchVBench Total score: 79.32 -> 79.64Improved
inject errors into target latents as well as context (ablation)Error Forcing · VBenchVBench Total score: 77.36 -> 79.64Improved
use a shared error instead of independent errors for context and target (ablation)Error Forcing · VBenchVBench Total score: 77.40 -> 79.64Improved
add ODE distillation before DMD to a bidirectional init (ablation)Bidirectional student · VBenchVBench Total score: 76.25 -> 80.79Improved
use error-aware causal init instead of bidirectional+ODE init (ablation)DMD student · VBenchVBench Total score: 80.79 -> 81.35Improved
add causal ODE distillation after error-aware causal pretraining (ablation)DMD student · VBenchVBench Total score: 81.35 -> 80.99Hurt

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