AI Paper Atlas

Research map / Video / Video generation

Delving into Latent Spectral Biasing of Video VAEs for Superior Diffusability

Shizhan Liu, Xinran Deng, Zhuoyi Yang, Jiayan Teng, Xiaotao Gu, Jie Tang

ECCV 2026 · Video › Video generation · approach: Efficient video diffusion models · 12 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
Add LMR and LCR (SSVAE) to 48-ch baseline VAEMMDiT 1.3B · VBench 17x512x512UR: 40.9 -> 45.9Improved
Add LCR to 48-ch baseline (ablation)VAE · MovieValidUR: 38.1 -> 39.0Improved
Add LMR on top of LCR (ablation)VAE · MovieValidUR: 39.0 -> 41.4Improved
Add decoder finetune after LMR (ablation)VAE · MovieValidUR: 41.4 -> 41.3No clear effect
Use LCR instead of SER or VA-VAE for low-frequency bias (ablation)64-ch VAE · URUR: 34.4 -> 35.5Improved
Add LCR to 64-ch VAE (ablation)64-ch VAE · FVDFVD: 553 -> 606Hurt
Over-bias LCR (omega=0.05, alpha=0.9) (ablation)LCR · URURHurt
SSVAE vs Wan 2.2 VAE at 17x256x256MMDiT 1.3B · VBenchFVD: 873 -> 983Mixed
SSVAE on Wan 1.3B backboneWan 1.3B · VBench 17x512x512UR: 37.7 -> 45.5Improved
Add LMR to LCR VAE (ablation)VAE · MovieValid reconstructionPSNR: 38.29 -> 37.84Hurt
Use LMR mask probabilities {0.7,0.1,0.1,0.1} vs no LMR (ablation)VAE · MovieValidUR: 39.2 -> 42.9Improved

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