AI Paper Atlas

Research map / Probabilistic and scientific modeling / Dynamical systems

From Embedding to Control: Representations for Stochastic Multi-Object Systems

Xiaoyuan Cheng, Yiming Yang, Wei Jiang, Chenyang Yuan, Zhuo Sun, Yukun Hu

ICLR 2026 · Probabilistic and scientific modeling › Dynamical systems · approach: State-space inference for stochastic systems

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
replace uniform neighbor weights (Hom) with mean-field adaptive weights (Hom+Mean) (ablation)GCE · Rope few-shot, 1 trajectorycontrol error: 0.74 -> 0.51Improved
replace Dense pair-wise operators with Hom+Mean (ablation)GCE · Rope few-shot, 1 trajectorycontrol error: 0.79 -> 0.51Improved
Hom+Mean versus Dense with 32 training trajectories (ablation)GCE · Rope few-shot, 32 trajectoriescontrol error: 0.26 -> 0.23Improved
use Gaussian potential instead of Laplace for interaction weights (ablation)GCE · Swim few-shotcontrol cost: 435.7 -> 404.3Improved
use Gaussian potential instead of vMF for interaction weights (ablation)GCE · Swim few-shotcontrol cost: 452.3 -> 404.3Improved
use a neural network (MLP) for the energy function instead of Gaussian kernel (ablation)GCE · multiple environmentsstabilityHurt
set Gaussian kernel bandwidth sigma to 2 rather than other values in 0.1 to 10 (ablation)GCE (Gaussian) · Rope and Soft few-shotcontrol error and costImproved
set feature dimension to 32 (ablation)GCE · Rope and Softcontrol errorImproved
use characteristic kernel features instead of polynomial features (KPM)GCE vs KPM · Power-Grid with 5% noisecontrol error: KPM NaN -> 0.39 ± 0.024Improved
use non-uniform mean-field weights instead of uniform weights (CKO)GCE vs CKO · Swim few-shotcontrol cost: 421.0 -> 404.3Improved
use GCE instead of CKO on in-distribution SwimGCE vs CKO · Swim in-distributioncontrol cost: 389.1 -> 383.7No clear effect
increase observation noise to 20% in Power-GridGCE vs CKO · Power-Grid 20% noisecontrol error: 0.85 -> 0.83No clear effect

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