# INTACT: Isomorphic Intent-to-Action Learning for Search-Free World Models

arXiv: https://arxiv.org/abs/2607.26056 · HTML: https://mlsanity.com/paper/2607.26056/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Embodied and robot world models, one of 11 directions in World models.
- Builds on 16 of its 39 references that are in the map.
- First posted on arXiv 28 Jul 2026.

## Placed in

- World models / [Embodied and robot world models](https://mlsanity.com/wm/embodied-and-robot-world-models/)

## Builds on (most cited first, 16 of 16)

- [Learning Latent Dynamics for Planning from Pixels](https://mlsanity.com/paper/1811.04551/) (2018)
- [Mastering Diverse Domains through World Models](https://mlsanity.com/paper/2301.04104/) (2023)
- [TD-MPC2: Scalable, Robust World Models for Continuous Control](https://mlsanity.com/paper/2310.16828/) (2023)
- [DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning](https://mlsanity.com/paper/2411.04983/) (2024)
- [LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels](https://mlsanity.com/paper/2603.19312/) (2026)
- [Unified World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasets](https://mlsanity.com/paper/2504.02792/) (2025)
- [DreamGen: Unlocking Generalization in Robot Learning through Video World Models](https://mlsanity.com/paper/2505.12705/) (2025)
- [Learning to Poke by Poking: Experiential Learning of Intuitive Physics](https://mlsanity.com/paper/1606.07419/) (2016)
- [Planning from Pixels using Inverse Dynamics Models](https://mlsanity.com/paper/2012.02419/) (2020)
- [Causal-JEPA: Learning World Models through Object-Level Latent Masking](https://mlsanity.com/paper/2602.11389/) (2026)
- [Sensorimotor World Models: Perception for Action via Inverse Dynamics](https://mlsanity.com/paper/2606.20104/) (2026)
- [Latent Geometry Beyond Search: Amortizing Planning in World Models](https://mlsanity.com/paper/2605.08732/) (2026)
- [What Makes Video World Model Latents Action-Relevant: Prediction over Reconstruction](https://mlsanity.com/paper/2606.07687/) (2026)
- [PRISM: PRior-guided Imagination Sampling in world Models](https://mlsanity.com/paper/2606.07974/) (2026)
- [QuoVLA: Quotient Space for Vision-Language-Action Models](https://mlsanity.com/paper/2605.24890/) (2026)
- [FiberTune: Preserving Action-Fiber Visual Residuals in Vision-Language-Action Fine-Tuning](https://mlsanity.com/paper/2606.08653/) (2026)

## Built on by (most cited first, 8 of 8)

- [VIScore: Diagnosing Planning-Relevant Quality in Latent World Models](https://mlsanity.com/paper/2608.11174/) (2026)
- [Representation World Model: Learning States, Transition and Executable Plans in Representation](https://mlsanity.com/paper/2609.29171/) (2026)
- [AD-WM: Action-Discriminative World Models for Counterfactual Model Predictive Control](https://mlsanity.com/paper/2609.30264/) (2026)
- [FlexiWorld: Learning and Planning via Flexible Action Chunks Across Multiple Time Scales](https://mlsanity.com/paper/2609.35138/) (2026)
- [Control-Geometry Straightening for Sampling-Based Latent Planning](https://mlsanity.com/paper/2609.35603/) (2026)
- [Beyond a single latent space: a dual-latent world model for long-horizon planning](https://mlsanity.com/paper/2609.37644/) (2026)
- [Social-WM: Safety-Aware Latent World Models for Robot Social Navigation](https://mlsanity.com/paper/2609.40177/) (2026)
- [Action-Consequence Alignment for Reliable Planning and Self-Improving in Latent World Models](https://mlsanity.com/paper/2610.04539/) (2026)

## Abstract (arXiv)

Forward latent world models predict how actions change a scene, but recover actions for a desired change only through expensive test-time search. We introduce INTACT (INtent-To-ACTion), an end-to-end JEPA that turns action-labeled, reward-free trajectories into a deployable intent-to-action interface. Each transition supplies physical intent zt+1-zt, while a future goal supplies deployment intent operatornamesg(zg)-zt. The architecture is isomorphic between the local and goal motion-intent backbone-input graphs through an identical four-slot grammar and shared parameters, and between supported local and goal motion-intent families through action-law semantics induced by the same predictor rather than pointwise latent equality. INTACT also provides intact transfer from RGB evidence to action-effective latent intent coordinates and from intent families to their corresponding action-law families. Asymmetric endpoint gradients ground physical successors and fix future goals as anchors, joining representation learning and control without pointwise latent matching or globally linear dynamics. The resulting coordinates support a robust distributional action law: its conditional mean serves directly as a search-free policy, while sampling remains available for diversity or optional verification. On the four official LeWM tasks, one-epoch, zero-search models reach 85.78%, 100.00%, 97.67%, and 97.89% success. Optional local CEM centered on the Direct plan reaches 96.86% macro success using 384 instead of 9,000 candidate sequences, reducing sampling by 23.44× while improving pure CEM by 16.00 points. One shared four-task encoder reaches 89.39% E5 Direct macro and improves every task over jointly trained LeWM, while predicted--expert action-family kNN tracks Direct success at r=0.954. Direct inference takes 2.9--5.5 ms.