AI Paper Atlas

Research map / Video / Video generation

MAD: Motion Appearance Decoupling for efficient Driving World Models

Ahmad Rahimi, Valentin Gerard, Eloi Zablocki, Matthieu Cord, Alexandre Alahi

CVPR 2026 · Video › Video generation · approach: World-model video generation · 5 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
decouple motion (pose video) and appearance stages instead of end-to-end LoRA fine-tuning of LTX (ablation)MAD-LTX 2B · OpenDV human preferencepreference count: 29 vs 16Improved
decouple motion and appearance instead of end-to-end fine-tuning (ablation)MAD-LTX 13B · OpenDV human preferencepreference count: 33 vs 15Improved
decouple motion and appearance instead of end-to-end fine-tuning (ablation)MAD-LTX 13B · OpenDV open-loop planningminADE6 (m): 5.83 -> 3.64Improved
decouple motion and appearance instead of end-to-end fine-tuning (ablation)MAD-LTX 13B · OpenDV open-loop planningAPD6 (cm): 63.06 -> 101.45Improved
standard end-to-end fine-tuning of base LTXLTX 13B · OpenDV open-loop planningminADE6 (m): 4.14 -> 5.83Hurt
standard end-to-end fine-tuning of base LTXLTX 2B · OpenDV open-loop planningminADE6 (m): 5.42 -> 5.28Improved
add targeted latent noise injection to appearance synthesizer pose conditioning (ablation)MAD-LTX 2B · OpenDV human preferencehuman preference for full model (%): 62%Improved
use pose skeleton representation instead of panoptic segmentation (ablation)MAD-LTX 2B · OpenDV human preferencehuman preference for pose model (%): 74%Improved
use pose skeleton representation instead of HDMap (ablation)MAD-LTX 2B · OpenDV human preferencehuman preference for pose model (%): 78%Improved
adapt SVD with MAD instead of VISTA-style full fine-tuningMAD-SVD · adaptation costGPU hours: 25,000 -> 1500Improved

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