# Policy-Guided World Model Planning for Language-Conditioned Visual Navigation

arXiv: https://arxiv.org/abs/2603.25981 · HTML: https://mlsanity.com/paper/2603.25981/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in World models for navigation, one of 11 directions in World models.
- Builds on 24 of its 31 references that are in the map.
- First posted on arXiv 26 Mar 2026.

## Placed in

- World models / [World models for navigation](https://mlsanity.com/wm/world-models-for-navigation/)

## Builds on (most cited first, 24 of 24)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [Octo: An Open-Source Generalist Robot Policy](https://mlsanity.com/paper/2405.12213/) (2024)
- [Mastering Diverse Domains through World Models](https://mlsanity.com/paper/2301.04104/) (2023)
- [Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments](https://mlsanity.com/paper/1711.07280/) (2017)
- [V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning](https://mlsanity.com/paper/2506.09985/) (2025)
- [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)
- [Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning](https://mlsanity.com/paper/1609.05143/) (2016)
- [Latent Action Pretraining from Videos](https://mlsanity.com/paper/2410.11758/) (2024)
- [LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics](https://mlsanity.com/paper/2511.08544/) (2025)
- [NoMaD: Goal Masked Diffusion Policies for Navigation and Exploration](https://mlsanity.com/paper/2310.07896/) (2023)
- [ViNT: A Foundation Model for Visual Navigation](https://mlsanity.com/paper/2306.14846/) (2023)
- [VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Model](https://mlsanity.com/paper/2602.10098/) (2026)
- [Dita: Scaling Diffusion Transformer for Generalist Vision-Language-Action Policy](https://mlsanity.com/paper/2503.19757/) (2025)
- [Learning Latent Action World Models In The Wild](https://mlsanity.com/paper/2601.05230/) (2026)
- [What Drives Success in Physical Planning with Joint-Embedding Predictive World Models?](https://mlsanity.com/paper/2512.24497/) (2025)
- [CLAP: Contrastive Latent Action Pretraining for Learning Vision-Language-Action Models from Human Videos](https://mlsanity.com/paper/2601.04061/) (2026)
- [CAST: Counterfactual Labels Improve Instruction Following in Vision-Language-Action Models](https://mlsanity.com/paper/2508.13446/) (2025)
- [An Efficient and Multi-Modal Navigation System with One-Step World Model](https://mlsanity.com/paper/2601.12277/) (2026)
- [UrbanNav: Learning Language-Guided Urban Navigation from Web-Scale Human Trajectories](https://mlsanity.com/paper/2512.09607/) (2025)

## Built on by (most cited first, 4 of 4)

- [PRISM: PRior-guided Imagination Sampling in world Models](https://mlsanity.com/paper/2606.07974/) (2026)
- [Skytopia: Monocular Drone Navigation with Action-Conditioned Latent World Models](https://mlsanity.com/paper/2609.26007/) (2026)
- [DroneWAM: Efficient World Action Model for Drone Visual Navigation](https://mlsanity.com/paper/2609.33148/) (2026)
- [Keeping JEPA World Models Plannable When Little of the Frame Moves](https://mlsanity.com/paper/2610.03137/) (2026)

## Abstract (arXiv)

Navigating to a visually specified goal given natural language instructions remains a fundamental challenge in embodied AI. Existing approaches either rely on reactive policies that struggle with long-horizon planning, or employ world models that suffer from poor action initialization in high-dimensional spaces. We present PiJEPA, a two-stage framework that combines the strengths of learned navigation policies with latent world model planning for instruction-conditioned visual navigation. In the first stage, we finetune an Octo-based generalist policy, augmented with a frozen pretrained vision encoder (DINOv2 or V-JEPA-2), on the CAST navigation dataset to produce an informed action distribution conditioned on the current observation and language instruction. In the second stage, we use this policy-derived distribution to warm-start Model Predictive Path Integral (MPPI) planning over a separately trained JEPA world model, which predicts future latent states in the embedding space of the same frozen encoder. By initializing the MPPI sampling distribution from the policy prior rather than from an uninformed Gaussian, our planner converges faster to high-quality action sequences that reach the goal. We systematically study the effect of the vision encoder backbone, comparing DINOv2 and V-JEPA-2, across both the policy and world model components. Experiments on real-world navigation tasks demonstrate that PiJEPA significantly outperforms both standalone policy execution and uninformed world model planning, achieving improved goal-reaching accuracy and instruction-following fidelity.