AI Paper Atlas

Research map / Probabilistic and scientific modeling / Dynamical systems

Controlled SDEs for Long-Horizon Motion Generation under Latent Decision Uncertainty

Han Zhang, Nenggan Zheng

ICML 2026 · Probabilistic and scientific modeling › Dynamical systems · approach: Latent-space control and planning

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 command-modulated drift to MoFlow (M1) (ablation)MoFlow · Rat Locomotion, horizon 60min ADE: 6.34 -> 4.12Improved
add stochastic diffusion to MoFlow (M2) (ablation)MoFlow · Rat Locomotion, horizon 60min ADE: 6.34 -> 3.55Improved
add both drift modulation and diffusion to MoFlow (M3, full CogSDE) (ablation)MoFlow · Rat Locomotion, horizon 60average ADE: 17.41 -> 10.41Improved
add diffusion on top of drift modulation (M1 to M3) (ablation)CogSDE · Rat Locomotion, horizon 60min ADE: 4.12 -> 3.79Hurt
add drift modulation on top of diffusion (M2 to M3) (ablation)CogSDE · Rat Locomotion, horizon 60min ADE: 3.55 -> 3.79Mixed
add drift modulation on top of diffusion (M2 to M3) (ablation)CogSDE · Rat Locomotion, horizon 60average ADE: 12.60 -> 10.41Improved
add boundedness regularizer lambda=0.001 (ablation)CogSDE · Rat Locomotion, horizon 60min ADE: 3.79 -> 3.65Improved
add boundedness regularizer lambda=0.001 (ablation)CogSDE · Rat Locomotion, horizon 60average ADE: 10.42 -> 12.37Hurt
add boundedness regularizer lambda=0.003 (ablation)CogSDE · Rat Locomotion, horizon 60average ADE: 10.42 -> 11.48Hurt
replace MoFlow with CogSDEMoFlow · Rat Locomotion, horizon 60min ADE: 6.34 -> 3.79Improved
use CogSDE instead of command-aware SLD-HMPSLD-HMP · BABEL, horizon 60min ADE: 0.023 -> 0.018Improved
use CogSDE instead of SLD-HMP on Rat LocomotionSLD-HMP · Rat Locomotion, horizon 60min ADE: 3.89 -> 3.79Improved

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