AI Paper Atlas

Research map / Video / Video generation

Model Already Knows the Best Noise: Bayesian Active Noise Selection via Attention in Video Diffusion Model

Kwanyoung Kim, Sanghyun Kim

ICLR 2026 · Video › Video generation · approach: Efficient video diffusion models

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 ANSE BANSA noise selectionAnimateDiff · VBenchtotal score: 77.98 -> 79.33Improved
add ANSE noise selectionCogVideoX-2B · VBenchtotal score: 81.03 -> 81.66Improved
add ANSE noise selectionCogVideoX-5B · VBenchtotal score: 81.52 -> 81.71Improved
add ANSE noise selectionHunyuanVideo · VBench aesthetic qualityaesthetic quality: 0.6276 -> 0.6268No clear effect
combine ANSE with FreqPriorFreqPrior · VBench (AnimateDiff)total score: 79.07 -> 80.43Improved
add ANSE noise selectionHunyuanVideo and Wan2.1 · MSR-VTTFVMD: 17641.19 -> 16491.68Improved
select seed by BANSA (B) instead of random (ablation)CogVideoX-2B · VBenchtotal score: 81.03 -> 81.66Improved
replace dropout with Bernoulli masking for BANSA (ablation)BANSA · VBenchtotal score: 81.33 -> 81.66Improved
use entropy acquisition instead of random (ablation)CogVideoX-2B · VBenchtotal score: 81.03 -> 81.13No clear effect
select highest BANSA seed (reverse criterion) (ablation)ANSE · VBenchquality score: 82.08 -> 81.93Hurt
increase ensemble size K from 1 to 10 (ablation)ANSE · VBench subject consistencysubject consistency: 0.9618 -> 0.9641Improved
add Bernoulli masking p=0.2 vs none (ablation)ANSE · VBench subject consistencysubject consistency: 0.9254 -> 0.9310Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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