AI Paper Atlas

Research map / Video / Action recognition

Factored Latent Action World Models

Zizhao Wang, Chang Shi, Jiaheng Hu, Kevin Rohling, Roberto Martín-Martín, Amy Zhang, Peter Stone

ICML 2026 · Video › Action recognition · approach: Action anticipation and latent actions · 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 causal temporal attention to the factorizer (ablation)FLAM · MultiGridPSNR: 51.6 -> 56.5Improved
Add causal temporal attention to the factorizer (ablation)FLAM · MultiGrid (DCI)disentanglement: 0.33 -> 0.91Improved
Add causal temporal attention to the factorizer (ablation)FLAM · MultiGridFVD: 36.6 -> 2.9Improved
Condition per-slot IDM on own next slot only instead of all slots (vs Global-Coupled) (ablation)FLAM · MultiGridPSNR: 56.3 -> 56.5No clear effect
Use per-slot latent actions instead of Global-Coupled variant (ablation)FLAM · MultiGrid (DCI)disentanglement: 0.79 -> 0.91Improved
Increase number of factors K from 2 to 4 (matching 4 agents) (ablation)FLAM · MultiGrid 4 agentsPSNR: 53.4 -> 56.5Improved
Increase number of factors K from 4 to 16 (ablation)FLAM · MultiGrid 4 agentsPSNR: 56.5 -> 56.5No clear effect
Increase KL coefficient beta from 1e-3 to 1e-2 (ablation)FLAM · MultiGridPSNR: 56.3 -> 24.9Hurt
Use factored latent actions (FLAM) instead of single monolithic latent action (AdaWorld)AdaWorld · Average over 5 datasetsPSNR: 24.7 -> 34.9Improved
Use FLAM instead of GenieGenie · Average over 5 datasetsFVD: 717.5 -> 419.6Improved
Use FLAM instead of PlaySlot (joint instead of two-stage object-centric training)PlaySlot · Average over 5 datasetsPSNR: 29.1 -> 34.9Improved
Use FLAM instead of ground-truth-action World ModelWorld Model · BigfishPSNR: 23.9 -> 30.8Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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