AI Paper Atlas

Research map / Video / Video generation

MEDUSA: Motion Elimination in Diffusion Using Spectral Attack

Hongwei Yu, Daoqing Zha, Xinlong Ding, Jiawei Li, Junbao Zhuo, Qiankun Liu, Huimin Ma, Jiansheng Chen

ICML 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
use nuclear-norm minimization instead of hard identity-matrix target (ablation)MEDUSA on SVD · SVD (50 images)Optical flow: 2.3325 -> 0.5980Improved
use nuclear-norm minimization instead of hard identity-matrix target (ablation)MEDUSA on SVD · SVD (50 images)Dynamic degree: 36.91% -> 7.23%Improved
target intermediate temporal block 5 instead of block 2 (ablation)MEDUSA on SVD · SVD (50 images)Optical flow: 2.7708 -> 0.5980Improved
target block 5 instead of block 8 (ablation)MEDUSA on SVD · SVD (50 images)Dynamic degree: 15.42% -> 7.23%Improved
apply JPEG compression defense to adversarial imageMEDUSA on SVD · SVDDynamic degree: 13.72% -> 21.93%Hurt
apply bit-depth reduction defenseMEDUSA on SVD · SVDOptical flow: 1.2246 -> 1.4172Hurt
MEDUSA vs Vid-Freezevideo attack · SVDOptical flow: 1.9099 -> 1.2246Improved
MEDUSA vs Vid-Freeze subject consistencyvideo attack · LTX-VideoSubject Consistency: 86.93% vs 85.67%Hurt
MEDUSA vs PhotoGuard on DynamiCraftervideo attack · DynamiCrafterDynamic degree: 57.21% -> 19.82%Improved
MEDUSA perturbation vs random Gaussian noiseMEDUSA · image qualitySSIM: 0.5454 -> 0.8202Improved
attack induces temporal rank collapseMEDUSA on SVD · SVDEffective rank: 7.74 -> 2.96Improved

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