AI Paper Atlas

Research map / Video / Video generation

Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation

Hongzhou Zhu, Min Zhao, Guande He, Hang Su, Chongxuan Li, Jun Zhu

ICML 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 AR teacher (causal ODE initialization) instead of bidirectional teacher for ODE distillation, chunk-wise (ablation)Causal Forcing (ODE init + DMD) · 100-prompt motion setDynamic Degree: 24 -> 68Improved
use AR teacher (causal ODE initialization), chunk-wise (ablation)Causal Forcing · 100-prompt motion setVisionReward: 3.330 -> 6.326Improved
use AR teacher (causal ODE initialization), frame-wise (ablation)Causal Forcing · 100-prompt motion setDynamic Degree: 2 -> 64Improved
use AR teacher (causal ODE initialization), frame-wise (ablation)Causal Forcing · 100-prompt motion setVisionReward: 1.951 -> 6.204Improved
train AR teacher with teacher forcing instead of diffusion forcing (ablation)AR diffusion training · 100-prompt motion setVisionReward: 1.583 -> 3.343Improved
train AR teacher with teacher forcing instead of diffusion forcing (ablation)AR diffusion training · 100-prompt motion setDynamic Degree: 60 -> 50Hurt
use causal CD with AR teacher instead of asymmetric CD (ablation)Consistency distillation · VBench TotalTotal score: 79.07 -> 81.48Improved
apply standard DMD only for AR student initialization (no causal ODE init) (ablation)Self Forcing · architectural gap isolationDynamic Degree / Instruction FollowingHurt
Causal Forcing versus Self Forcing at same latencyDistilled AR video models · 100-prompt motion setDynamic Degree: 57 -> 68Improved

Later papers that compared with this method

13 later accepted papers report Causal Forcing as a baseline in their results tables; 13 of them report a better number on most of the results they share with it.

5 more not listed.

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