AI Paper Atlas

Research map / Video / Video segmentation and tracking

Latent Particle World Models: Self-supervised Object-centric Stochastic Dynamics Modeling

Tal Daniel, Carl Qi, Dan Haramati, Amir Zadeh, Chuan Li, Aviv Tamar, Deepak Pathak, David Held

ICLR 2026 · Video › Video segmentation and tracking · approach: Stochastic video prediction · 8 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
use object-centric particles instead of patch-based DVAEworld model · Sketchy-ULPIPS: 0.113 -> 0.070Improved
use object-centric particles instead of patch-based DVAEworld model · Mario-UFVD: 277.41 -> 195.95Improved
use object-centric particles instead of patch-based DVAEworld model · Bridge-LFVD: 146.85 -> 47.78Improved
use object-centric particles instead of patch-based DVAEworld model · LanguageTable-LFVD: 26.78 -> 15.96Improved
use object-centric particles instead of patch-based DVAEworld model · BAIR-UFVD: 164.41 -> 163.91No clear effect
use object-centric particles instead of patch-based DVAEworld model · LanguageTable-ALPIPS: 0.038 -> 0.037No clear effect
use per-particle latent actions instead of PlaySlot global latent actionvideo prediction · Sketchy-ULPIPS: 0.275 -> 0.070Improved
use per-particle latent actions rather than global latent actions (ablation)LPWM · video predictionperformanceImproved
embed positions via AdaLN instead of additive positional embeddings (ablation)LPWM · video predictionperformanceImproved
vary latent action dimension near the particle dimension (ablation)LPWM · video predictionperformanceNo clear effect
use LPWM instead of EC Diffuser on PandaPushimitation learning · PandaPush 2 Cubessuccess rate (%): 91.7 -> 74Hurt
use LPWM instead of HIQL on OGBench-Sceneimitation learning · OGBench-Scene task3success rate (%): 61 -> 89Improved

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