AI Paper Atlas

Research map / Video / Video generation

LinVideo: A Post-Training Framework towards O(n) Attention in Efficient Video Generation

Yushi Huang, Xingtong Ge, Ruihao Gong, Chengtao Lv, Jun Zhang

CVPR 2026 · Video › Video generation · approach: Efficient video diffusion models · 11 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 learned selective transfer instead of manual layer choice (ablation)LinVideo · VBench (5 dims)Imaging Quality: 62.97 -> 66.07Improved
add learned selective transfer instead of heuristic grid search (ablation)LinVideo · VBench (5 dims)Imaging Quality: 60.74 -> 66.07Improved
add regularization Lreg (ablation)LinVideo · VBench (5 dims)Imaging Quality: 18.62 -> 66.07Improved
use ADM objective instead of MSE (ablation)LinVideo · VBench (5 dims)Imaging Quality: 61.56 -> 66.07Improved
use ADM instead of few-step DMD loss (ablation)LinVideo · VBench (5 dims)Imaging Quality: 57.44 -> 66.07Improved
estimate score with the model itself instead of an extra score model (ablation)LinVideo · VBench (5 dims)Overall Consistency: 25.87 -> 26.52Improved
self-score estimation reduces training time (ablation)LinVideo · training costtraining time: ~4.4x lessImproved
increase target linear layers from 16 to 20 (ablation)LinVideo · VBench (5 dims)Imaging Quality: 66.07 -> 64.38; latency 68.26 -> 61.68Hurt
increase target linear layers from 10 to 16 (ablation)LinVideo · VBench (5 dims)Imaging Quality: 66.32 -> 66.07No clear effect
vary coefficient of Lcon+Lreg from 0.1 to 0.001 (ablation)LinVideo · VBench (5 dims)Imaging Quality: 66.21 / 65.98 vs 66.07No clear effect
apply LinVideo versus FlashAttention2Wan 1.3B · VBench-2.0total score: 56.74 vs 56.74No clear effect
apply LinVideo versus FlashAttention2Wan 14B · VBench-2.0total score: 59.85 -> 59.62Hurt

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