AI Paper Atlas

Research map / Video / Video generation

UniTemp: Unlocking Video Generation in Any Temporal Order via Autoregressive Distillation

Lin Zhang, Sicheng Mo, Zefan Cai, Jinhong Lin, Zihao Lin, Jiuxiang Gu, Krishna Kumar Singh, Yuheng Li, Yin Li

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 3 blockwise anchor latents in backward generation (ablation)UniTemp backward · Flickering ratio inter-blockinter-block FR: 1.42 -> 1.07Improved
add 1 anchor latent (ablation)UniTemp backward · Flickering ratio inter-blockinter-block FR: 1.42 -> 1.26Improved
add 2 anchor latents (ablation)UniTemp backward · Flickering ratio inter-blockinter-block FR: 1.42 -> 1.23Improved
include anchor latents as output at inference (ablation)UniTemp backward P=3 · Flickering ratio inter-blockinter-block FR: 1.07 -> 1.46Hurt
include anchor latents as output in training and inference (ablation)UniTemp backward P=3 · Flickering ratio inter-blockinter-block FR: 1.08 -> 1.48Hurt
share generator and fake critic across directions (ablation)UniTemp forward · VBench short 5sVBench Total: 83.42 -> 83.81Improved
share generator and fake critic across directions (ablation)UniTemp backward · VBench short 5sVBench Total: 84.26 -> 84.23No clear effect
share generator only (ablation)UniTemp backward · VBench short 5sVBench Total: 84.26 -> 83.96Hurt
anchor latents vs none for backward generation, user preference (ablation)UniTemp backward · User study A/B (200 responses)preference rate: 87% vs 13%Improved
add future sink latents to forward long generation (ablation)UniTemp forward · Long video 100sdynamic degree: 87.50 -> 44.50Hurt
add future sink latents to forward long generation (ablation)UniTemp forward · Long video 100ssubject consistency: 93.95 -> 97.30Improved
add past sink latents to backward generation with future sink (ablation)UniTemp backward · Long video 100ssubject consistency: 93.94 -> 96.75Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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