# Value-guided action planning with JEPA world models

arXiv: https://arxiv.org/abs/2601.00844 · HTML: https://mlsanity.com/paper/2601.00844/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Placed in Latent predictive world models, one of 11 directions in World models.
- Builds on 15 of its 18 references that are in the map.
- First posted on arXiv 28 Dec 2025.

## Placed in

- World models / [Latent predictive world models](https://mlsanity.com/wm/latent-predictive-world-models/)

## Builds on (most cited first, 15 of 15)

- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [D4RL: Datasets for Deep Data-Driven Reinforcement Learning](https://mlsanity.com/paper/2004.07219/) (2020)
- [Offline Reinforcement Learning with Implicit Q-Learning](https://mlsanity.com/paper/2110.06169/) (2021)
- [Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2301.08243/) (2023)
- [Revisiting Feature Prediction for Learning Visual Representations from Video](https://mlsanity.com/paper/2404.08471/) (2024)
- [DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning](https://mlsanity.com/paper/2411.04983/) (2024)
- [HIQL: Offline Goal-Conditioned RL with Latent States as Actions](https://mlsanity.com/paper/2307.11949/) (2023)
- [Optimal Goal-Reaching Reinforcement Learning via Quasimetric Learning](https://mlsanity.com/paper/2304.01203/) (2023)
- [Foundation Policies with Hilbert Representations](https://mlsanity.com/paper/2402.15567/) (2024)
- [Learning from Reward-Free Offline Data: A Case for Planning with Latent Dynamics Models](https://mlsanity.com/paper/2502.14819/) (2025)
- [Reinforcement Learning from Passive Data via Latent Intentions](https://mlsanity.com/paper/2304.04782/) (2023)
- [A Policy-Guided Imitation Approach for Offline Reinforcement Learning](https://mlsanity.com/paper/2210.08323/) (2022)
- [Improved Representation of Asymmetrical Distances with Interval Quasimetric Embeddings](https://mlsanity.com/paper/2211.15120/) (2022)
- [Deep Value Model Predictive Control](https://mlsanity.com/paper/1910.03358/) (2019)
- [Infinite-Horizon Value Function Approximation for Model Predictive Control](https://mlsanity.com/paper/2502.06760/) (2025)

## Built on by (most cited first, 22 of 22)

- [VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Model](https://mlsanity.com/paper/2602.10098/) (2026)
- [Predictive but Not Plannable: RC-aux for Latent World Models](https://mlsanity.com/paper/2605.07278/) (2026)
- [VJEPA: Variational Joint Embedding Predictive Architectures as Probabilistic World Models](https://mlsanity.com/paper/2601.14354/) (2026)
- [Temporal-Distance JEPA: Plan-Aware Representation Learning for Latent World Model Predictive Control](https://mlsanity.com/paper/2607.25337/) (2026)
- [Human Cognition in Machines: A Unified Perspective of World Models](https://mlsanity.com/paper/2604.16592/) (2026)
- [A Generalization Theory for JEPA-Based World Models](https://mlsanity.com/paper/2606.27014/) (2026)
- [BiJEPA: Bi-directional Joint Embedding Predictive Architecture for Symmetric Representation Learning](https://mlsanity.com/paper/2603.00049/) (2026)
- [AeroJEPA: Learning Semantic Latent Representations for Scalable 3D Aerodynamic Field Modeling](https://mlsanity.com/paper/2605.05586/) (2026)
- [Qantara: Bridge-Flow Training for Multi-Paradigm JEPA Control](https://mlsanity.com/paper/2607.04978/) (2026)
- [SCALE: State-Calibrated Latent Embeddings for JEPA Planning in the Right Geometry](https://mlsanity.com/paper/2608.16287/) (2026)
- [Gaussian Joint Embeddings For Self-Supervised Representation Learning](https://mlsanity.com/paper/2603.26799/) (2026)
- [Latent State Design for World Models under Sufficiency Constraints](https://mlsanity.com/paper/2605.01694/) (2026)
- [Traj-LeWM: Path-Aware World-Model Planning via Latent Trajectory Cost](https://mlsanity.com/paper/2608.14125/) (2026)
- [Grounded World Model for Semantically Generalizable Planning](https://mlsanity.com/paper/2604.11751/) (2026)
- [Intrinsic-Energy Joint Embedding Predictive Architectures Induce Quasimetric Spaces](https://mlsanity.com/paper/2602.12245/) (2026)
- [Finite-Sample Metric Non-Collapse for Geometrically Supervised Latent World Models in Control](https://mlsanity.com/paper/2608.07265/) (2026)
- [World Simulator: Queer Erotica and the Absurdity of AI Video Models That Promise the World](https://mlsanity.com/paper/2608.07510/) (2026)
- [Neither Adversarial Training Nor Purification: Emergent Adversarial Robustness from Oscillatory Predictive Learning](https://mlsanity.com/paper/2609.08683/) (2026)
- [I Act Therefore I Am: When Is JEPA's Action-Conditioning Enough to Learn Causal Mechanisms?](https://mlsanity.com/paper/2609.31161/) (2026)
- [Control-Geometry Straightening for Sampling-Based Latent Planning](https://mlsanity.com/paper/2609.35603/) (2026)
- [When Low Prediction Error Misleads Planning: Diagnosing Representation, Dynamics, and Decision Failures in Latent World Models](https://mlsanity.com/paper/2610.05550/) (2026)
- [Agentic Large Language Models](https://mlsanity.com/paper/2610.13455/) (2026)

## Abstract (arXiv)

Building deep learning models that can reason about their environment requires capturing its underlying dynamics. Joint-Embedded Predictive Architectures (JEPA) provide a promising framework to model such dynamics by learning representations and predictors through a self-supervised prediction objective. However, their ability to support effective action planning remains limited. We propose an approach to enhance planning with JEPA world models by shaping their representation space so that the negative goal-conditioned value function for a reaching cost in a given environment is approximated by a distance (or quasi-distance) between state embeddings. We introduce a practical method to enforce this constraint during training and show that it leads to significantly improved planning performance compared to standard JEPA models on simple control tasks.