# Latent World Models with Monotone Planning Costs for Image-Goal Navigation

arXiv: https://arxiv.org/abs/2608.09073 · HTML: https://mlsanity.com/paper/2608.09073/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in World models for navigation, one of 11 directions in World models.
- Builds on 15 of its 36 references that are in the map.
- First posted on arXiv 10 Aug 2026.

## Placed in

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

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

- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Mastering Diverse Domains through World Models](https://mlsanity.com/paper/2301.04104/) (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)
- [Navigation World Models](https://mlsanity.com/paper/2412.03572/) (2024)
- [NoMaD: Goal Masked Diffusion Policies for Navigation and Exploration](https://mlsanity.com/paper/2310.07896/) (2023)
- [VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Model](https://mlsanity.com/paper/2602.10098/) (2026)
- [Vid2World: Crafting Video Diffusion Models to Interactive World Models](https://mlsanity.com/paper/2505.14357/) (2025)
- [Back to the Features: DINO as a Foundation for Video World Models](https://mlsanity.com/paper/2507.19468/) (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)
- [Hierarchical Planning with Latent World Models](https://mlsanity.com/paper/2604.03208/) (2026)
- [OmniVLA: An Omni-Modal Vision-Language-Action Model for Robot Navigation](https://mlsanity.com/paper/2509.19480/) (2025)
- [CAST: Counterfactual Labels Improve Instruction Following in Vision-Language-Action Models](https://mlsanity.com/paper/2508.13446/) (2025)
- [X-MOBILITY: End-To-End Generalizable Navigation via World Modeling](https://mlsanity.com/paper/2410.17491/) (2024)

## Built on by (most cited first, 5 of 5)

- [FIRM-WM: State-factorized factual-interventional recurrent modeling for reward-free visual planning](https://mlsanity.com/paper/2609.22816/) (2026)
- [Visual Representation and History Modeling for Navigation World Models](https://mlsanity.com/paper/2609.29555/) (2026)
- [Aim Short to Reach Far: Your Frozen World Model Can Plan Better Than You Think](https://mlsanity.com/paper/2609.30036/) (2026)
- [In CEM, a World Model Is Also a Proposal Mechanism](https://mlsanity.com/paper/2610.00921/) (2026)
- [When Low Prediction Error Misleads Planning: Diagnosing Representation, Dynamics, and Decision Failures in Latent World Models](https://mlsanity.com/paper/2610.05550/) (2026)

## Abstract (arXiv)

Image-goal navigation with latent world models requires not only accurate future prediction, but also a planning cost that reliably ranks candidate action sequences. We define the cost as the cosine distance between the predicted future embedding and the goal embedding, and show that poor cost ordering can mislead sampling-based planners such as Cross-Entropy Method (CEM). To address this, we propose a latent world model built on a frozen DINO-family encoder and train it with two complementary objectives. An autoregressive rollout loss reduces the gap between training and multi-step planning rollouts, while a Monotone Cost Ranking (MCR) loss directly encourages increasingly perturbed action sequences to receive higher planning costs. We also study InfoNCE-based action-contrastive training and find that temporal permutation negatives distort the latent geometry and degrade planning performance. On the GNM navigation dataset, our method outperforms Navigation World Models (NWM), DINO-WM, OmniVLA, and NoMaD, achieving state-of-the-art image-goal navigation performance while reducing orientation error by 2.7× over the same-encoder DINO WM baseline. We also deploy the model zero-shot on a physical robot, where it follows goal-directed paths in unseen indoor and outdoor environments.