AI Paper Atlas

Research map / Probabilistic and scientific modeling / Dynamical systems

Stochastic Lifting for Generating Trajectories of Stochastic Physical Systems

Jules Berman, Tobias Blickhan, Benjamin Peherstorfer

ICML 2026 · Probabilistic and scientific modeling › Dynamical systems · approach: Stochastic population dynamics · 0 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 stochastic lifting (SL, 1 step) in place of ARDM with 40 diffusion stepsautoregressive generation · WaveW2 crossing time: 1.11e-2 -> 4.53e-3Improved
add stochastic lifting (1 step) in place of ARDM with 40 stepsautoregressive generation · FlowW2 crossing time: 1.86e-3 -> 9.47e-4Improved
add stochastic lifting (1 step) in place of ARDM with 40 stepsautoregressive generation · FlowW2 integrated mass: 6.00e-4 -> 6.08e-4No clear effect
increase ARDM diffusion steps from 2 to 20 (ablation)ARDM · FlowW2 crossing time: 1.18e-1 -> 3.25e-2Improved
increase ARDM diffusion steps from 20 to 40 (ablation)ARDM · WaveW2 crossing time: 7.28e-3 -> 1.11e-2Hurt
increase ARDM diffusion steps from 2 to 40 (ablation)ARDM · FlowW2 integrated mass: 3.46e-2 -> 6.00e-4Improved
shuffle a growing share of training pairs (x_t, x_t+1) (ablation)Stochastic Lifting · Duffing oscillator (SDE)W2 errorHurt
increase label dimension until interpolation is reached (ablation)Stochastic Lifting · Duffing oscillator (SDE)final training loss: one order-of-magnitude lower L2 final training lossImproved
increase label dimension (ablation)Stochastic Lifting · Duffing oscillator (SDE)network gradient normImproved
increase label dimension beyond the interpolation threshold (ablation)Stochastic Lifting · WaveW2 crossing timeNo clear effect
map directly from initial condition to final state instead of sequential rollout (ablation)Stochastic Lifting · Wave and Flowsample qualityHurt
add stochastic lifting versus the best one-step baseline NUWAone-step video generation · BAIR video generationFVD: 86.9 -> 69.0Improved

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