AI Paper Atlas

Research map / Video / Video generation

NS-Diff: Fluid Navier-Stokes Guided Video Diffusion via Reinforcement Learning

Zijun Deng, Yuxin Peng

CVPR 2026 · Video › Video generation · approach: Efficient video diffusion models

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 physics-guided RL with latent injection to OpenSora2-11BOpenSora2-11B · PhysVideoBench testJerk error (ΔJ): 0.69 -> 0.25Improved
add physics-guided RL with latent injection to OpenSora2-11BOpenSora2-11B · UCF-101FVD: 110 -> 85Improved
add physics-guided RL with latent injection to OpenSora2OpenSora2 · WebVid-10M text-to-videoFVD: 297 -> 275Improved
add PPO optimization on top of the physics losses (ablation)NS-Diff-DiT 1B · PhysVideoBench (1B DiT ablation)Jerk error (ΔJ): 0.58 -> 0.33Improved
add physics-conditioned latent injection (ablation)NS-Diff-DiT 1B · PhysVideoBench (1B DiT ablation)Jerk error (ΔJ): 0.82 -> 0.33Improved
add physics constraints (rigid and fluid losses) (ablation)NS-Diff-DiT 1B · PhysVideoBench (1B DiT ablation)Jerk error (ΔJ): 1.21 -> 0.33Improved
add adaptive activation scheduler (ablation)NS-Diff-DiT 1B · PhysVideoBench (1B DiT ablation)Jerk error (ΔJ): 0.67 -> 0.33Improved
use adaptive scheduler instead of linear scheduler (ablation)NS-Diff-DiT 1B · PhysVideoBench (1B DiT ablation)FVD: 207 -> 183Improved
add fluid Navier-Stokes loss (ablation)NS-Diff-DiT 1B · PhysVideoBench (1B DiT ablation)Fluid divergence error (Ldiv, x10^-3): 10.4 -> 2.9Improved
add rigid jerk loss (ablation)NS-Diff-DiT 1B · PhysVideoBench (1B DiT ablation)Jerk error (ΔJ): 1.33 -> 0.33Improved
remove fluid loss on jerk metric (ablation)NS-Diff-DiT 1B · PhysVideoBench (1B DiT ablation)Jerk error (ΔJ): 0.33 -> 0.49 (w/o Lfluid)Mixed
estimate flow on decoded RGB proxies instead of directly in latent space (ablation)ARFlow · PhysVideoBench (1B DiT ablation)FVD: 205 -> 183Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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