AI Paper Atlas

Research map / Video / Video generation

Latent Knowledge-Guided Video Diffusion for Scientific Phenomena Generation from a Single Initial Frame

Qinglong Cao, Xirui Li, Ding Wang, Chao Ma, Yuntian Chen, Xiaokang Yang

AAAI 2026 · Video › Video generation · approach: Efficient video diffusion models · 16 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 latent scientific knowledge and quaternion prompts to SVDSVD · DamBreak simulationRMSE: 8.189 -> 4.921Improved
add latent scientific knowledge and quaternion prompts to CogVideoXCogVideoX · DepthCharge simulationRMSE: 4.775 -> 3.990Improved
use method vs LoRA fine-tuning on typhoon dataSVD · Typhoon 202001SSIM: 0.365 -> 0.446Improved
add the method on typhoon continuity scoreSVD/CogVideoX · Typhoon 202001CS: 16.66 -> 19.19Hurt
add static knowledge (MAE embeddings) (ablation)Ours(SVD) · Cylinder simulationRMSE: 6.021 -> 5.852Improved
add dynamic knowledge (optical flow embeddings) (ablation)Ours(SVD) · Cylinder simulationRMSE: 5.983 -> 5.852Improved
add spatial-domain modeling (ablation)Ours(SVD) · Cylinder simulationRMSE: 6.423 -> 5.852Improved
add frequency-domain modeling (ablation)Ours(SVD) · Cylinder simulationRMSE: 5.923 -> 5.852Improved
use quaternion network instead of linear projection (ablation)Ours(SVD) · Cylinder simulationRMSE: 5.913 -> 5.852Improved
use quaternion projection instead of cross attention (ablation)Ours(SVD) · Cylinder simulationSFE: 70.012 -> 62.456Improved
vary LoRA rank from 4 to 2 or 8 (ablation)Ours(SVD) · Cylinder simulationRMSE: 5.852 -> 6.132 (rank 2), 6.018 (rank 8)Hurt

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