AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

VideoMAETok: Boosting Video Diffusion Models via Masked Autoencoders as Tokenizers

Zhan Tong, Tinne Tuytelaars

ICML 2026 · Image generation › Autoregressive and latent generation · approach: Latent diffusion with learned tokenizers

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 high-ratio token masking (ablation)VideoMAETok S-B · UCF-101, SiT-BgFVD: 418.8 -> 220.8Improved
add interpolative latent noise (ablation)VideoMAETok S-B · UCF-101, SiT-BgFVD: 418.8 -> 178.8Improved
combine masking and latent noise (ablation)VideoMAETok S-B · UCF-101, SiT-BgFVD: 418.8 -> 106.2Improved
combine masking and latent noise (ablation)VideoMAETok S-B · Kinetics-400 val reconstructionrFVD: 6.0 -> 19.8Hurt
increase reconstruction loss weight 10x (ablation)VideoMAETok S-B · UCF-101, SiT-BgFVD: 106.2 -> 3998.2Hurt
increase latent channels from 16 to 32 (ablation)VideoMAETok S-B · UCF-101, SiT-BgFVD: 106.2 -> 3948Hurt
increase latent channels from 4 to 16 (ablation)VideoMAETok S-B · UCF-101, SiT-BgFVD: 1427 -> 106.2Improved
use causal attention instead of non-causal (ablation)VideoMAETok S-B · UCF-101, SiT-BgFVD: 106.2 -> 125.4Hurt
scale tokenizer from ViT S-S to B-L (ablation)VideoMAETok · UCF-101, SiT-BgFVD: 172.9 -> 87.7Improved
scale generator from SiT-B to SiT-XL (ablation)VideoMAETok S-B · UCF-101gFVD: 106.2 -> 82.2Improved
use heavier decoder than encoder (asymmetric design) (ablation)VideoMAETok · UCF-101, SiT-BgFVD: 172.9 (S-S) -> 106.2 (S-B)Improved
raise masking ratio from 0.8 to 0.9 (ablation)VideoMAETok S-B · UCF-101, SiT-BgFVD: 106.2 -> degraded at 0.9Hurt

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