AI Paper Atlas

Research map / Probabilistic and scientific modeling / Dynamical systems

Meta-iLaD: Identifiable Latent Dynamics via Meta-Learning of Dynamics Environments

Yubo Ye, Sweekar Piya, Xiajun Jiang, Linwei Wang

ICML 2026 · Probabilistic and scientific modeling › Dynamical systems · approach: Latent dynamics 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
infer c from few-shot context samples instead of the query sample (ablation)Meta-iLaD · Pendulum OODMCC(c): 0.88 -> 0.96Improved
infer c from few-shot context samples instead of the query sample (ablation)Meta-iLaD · Pendulum predictionMSE(x): 5.06(0.50)e-1 -> 3.49(0.40)e-1Improved
use context samples instead of predefined environment index (ablation)Meta-iLaD · Pendulum predictionMSE(x): 3.45(0.22)e-1 vs 3.49(0.40)e-1No clear effect
use context samples instead of predefined labels (enables OOD) (ablation)Meta-iLaD · Pendulum OODMSE(x): predefined index: not applicable; context 6.16(0.08)e-1Improved
add TC regularization (ablation)Meta-iLaD · Pendulum predictionMCC(c): 0.88 -> 0.98Improved
add warm-up training (L_flow) (ablation)Meta-iLaD · Pendulum predictionMCC(z): 0.26 -> 1.00Improved
add warm-up training (L_flow) (ablation)Meta-iLaD · Pendulum predictionMSE(x): 3.58(0.27)e0 -> 4.82(0.22)e-1Improved
use identifiable latent environment c with context samples vs IDF process noiseMeta-iLaD · Pendulum predictionMCC(c): 0.02(0.01) -> 0.98(0.01)Improved
use Meta-iLaD instead of IDF on OOD subjectMeta-iLaD · MoCAP OOD predictionMSE: 1.18(0.06)e2 -> 7.87(1.25)e1Improved
identifiability of c and F matters for prediction but not reconstructionMeta-iLaD vs IDF · PendulumMSE(x): reconstruction 3.78(0.34)e-1 vs 3.58(0.27)e-1; prediction 1.26(0.47)e1 vs 3.56(0.35)e-1Improved

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