AI Paper Atlas

Research map / Video / Video generation

SteinsGate: Adding Causality to Diffusions for Long Video Generation via Path Integral

Yufei Huang, Liangyu Yuan, Changxi Chi, Yunfan Liu, Cheng Tan, Siyuan Li, Jingbo Zhou, Haitao Lin, Chang Yu, Stan Z. Li

ICLR 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 Video Path Integral to I2V-AR continuation (ablation)SteinsGate (Wan2.1) · InstructVC benchmark (multi-action long video)CSCV: 0.74 -> 0.82Improved
add Video Path Integral to I2V-AR continuation (ablation)SteinsGate (Wan2.1) · InstructVC benchmark (multi-action long video)motion smoothness: 0.94 -> 0.97Improved
add Guidance Interval (VPI only in high-noise stage) (ablation)SteinsGate · InstructVC benchmark (multi-action long video)CSCV: 0.81 -> 0.82No clear effect
add History-aligned Redistribution (ablation)SteinsGate · InstructVC benchmark (multi-action long video)CSCV: 0.79 -> 0.82Improved
add Path Convergence Guidance (ablation)SteinsGate · InstructVC benchmark (multi-action long video)CSCV: 0.78 -> 0.82Improved
use SteinsGate instead of other training-free methods (DiTCtrl, FIFO)inference-time long video generation · InstructVC benchmark (multi-action long video)CSCV: 0.76 -> 0.82 (vs DiTCtrl); 0.71 -> 0.82 (vs FIFO)Improved
use SteinsGate (training-free) vs training-based diffusion forcing (SkyReel-V2, MAGI-1)SteinsGate · InstructVC benchmark (multi-action long video)CSCV: 0.83 / 0.82 vs 0.82No clear effect
replace Temporal Action Binding with concatenated prompts and equal durations (ablation)SteinsGate · InstructVC benchmark (multi-action long video)action completeness/orderImproved
raise PCG weight from 1.0 to 1.5 (extrapolation) (ablation)Path Convergence Guidance · InstructVC benchmark (multi-action long video)CSCV: 0.78 -> 0.82Improved
raise selected history frames K from 1 to 3 (ablation)Video Path Integral · InstructVC benchmark (multi-action long video)CSCV: 0.74 -> 0.82Improved
increase history ratio from 20% to 30% of segment length (ablation)SteinsGate · InstructVC benchmark (multi-action long video)CSCV: 0.82 -> 0.79Hurt
add Video Path Integral to I2V-ARSteinsGate · inference cost 15 s videogeneration time (min): 30 -> 38Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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