# WNM-3D: A World Navigation Model with 3D Scene Conditioning for Closed-Loop VLN

arXiv: https://arxiv.org/abs/2608.07267 · HTML: https://mlsanity.com/paper/2608.07267/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 36 of its 41 references that are in the map.
- First posted on arXiv 7 Aug 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)
- Vision-language-action models / [World model-based VLA](https://mlsanity.com/vla/world-model-based-vla/)

## Builds on (most cited first, 30 of 36)

- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [On Evaluation of Embodied Navigation Agents](https://mlsanity.com/paper/1807.06757/) (2018)
- [World Action Models are Zero-shot Policies](https://mlsanity.com/paper/2602.15922/) (2026)
- [DanceGRPO: Unleashing GRPO on Visual Generation](https://mlsanity.com/paper/2505.07818/) (2025)
- [Navigation World Models](https://mlsanity.com/paper/2412.03572/) (2024)
- [NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation](https://mlsanity.com/paper/2402.15852/) (2024)
- [NaVILA: Legged Robot Vision-Language-Action Model for Navigation](https://mlsanity.com/paper/2412.04453/) (2024)
- [InstructNav: Zero-shot System for Generic Instruction Navigation in Unexplored Environment](https://mlsanity.com/paper/2406.04882/) (2024)
- [Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Tasks](https://mlsanity.com/paper/2412.06224/) (2024)
- [Embodied Navigation Foundation Model](https://mlsanity.com/paper/2509.12129/) (2025)
- [RoboGSim: A Real2Sim2Real Robotic Gaussian Splatting Simulator](https://mlsanity.com/paper/2411.11839/) (2024)
- [AI Flow at the Network Edge](https://mlsanity.com/paper/2411.12469/) (2024)
- [AI Flow: Perspectives, Scenarios, and Approaches](https://mlsanity.com/paper/2506.12479/) (2025)
- [GaussianDiffusion: 3D Gaussian Splatting for Denoising Diffusion Probabilistic Models with Structured Noise](https://mlsanity.com/paper/2311.11221/) (2023)
- [Find What You Want: Learning Demand-conditioned Object Attribute Space for Demand-driven Navigation](https://mlsanity.com/paper/2309.08138/) (2023)
- [DriveDreamer-Policy: A Geometry-Grounded World-Action Model for Unified Generation and Planning](https://mlsanity.com/paper/2604.01765/) (2026)
- [Learning 4D Geometric Priors for Inference-Efficient World Action Models](https://mlsanity.com/paper/2607.05468/) (2026)
- [WorldVLN: Autoregressive World Action Model for Aerial Vision-Language Navigation](https://mlsanity.com/paper/2605.15964/) (2026)
- [From Seeing to Experiencing: Scaling Navigation Foundation Models with Reinforcement Learning](https://mlsanity.com/paper/2507.22028/) (2025)
- [GeoSem-WAM: Geometry- and Semantic-Aware World Action Models](https://mlsanity.com/paper/2606.03188/) (2026)
- [Sparse Video Generation Propels Real-World Beyond-the-View Vision-Language Navigation](https://mlsanity.com/paper/2602.05827/) (2026)
- [WAM-Nav: Asymmetric Latent World-Action Modeling for Unified Visual Navigation](https://mlsanity.com/paper/2606.04907/) (2026)
- [NavWAM: A Navigation World Action Model for Goal-Conditioned Visual Navigation](https://mlsanity.com/paper/2606.13494/) (2026)
- [CogDDN: A Cognitive Demand-Driven Navigation with Decision Optimization and Dual-Process Thinking](https://mlsanity.com/paper/2507.11334/) (2025)
- [FutureNav: Unified World-Action Modeling for Vision-and-Language Navigation](https://mlsanity.com/paper/2606.30367/) (2026)
- [GN0: Toward a Unified Paradigm for Generation, Evaluation, and Policy Learning in Visual-Language Navigation](https://mlsanity.com/paper/2606.03682/) (2026)
- [WorldFly: A World-Model-Based Vision-Language-Action Model for UAV Navigation](https://mlsanity.com/paper/2606.06147/) (2026)
- [DeCoNav: Dialog enhanced Long-Horizon Collaborative Vision-Language Navigation](https://mlsanity.com/paper/2604.12486/) (2026)
- [NavWM: A Unified Navigation World Model for Foresight-Driven Planning](https://mlsanity.com/paper/2606.24101/) (2026)

## Built on by (most cited first, 2 of 2)

- [RiverVLN: Phase-Grounded Temporal Vision--Language Navigation for Unmanned Surface Vehicles](https://mlsanity.com/paper/2609.23423/) (2026)
- [AVERT-VLN: Abstention-aware Visual Error Recovery and Training for Vision-and-Language Navigation](https://mlsanity.com/paper/2609.39579/) (2026)

## Abstract (arXiv)

Recent vision-language navigation (VLN) systems increasingly adapt pretrained vision-language models (VLMs) into vision-language-action (VLA) policies that map egocentric observations and language instructions directly to navigation actions. Although semantically capable, such action-centric training does not explicitly model how the agent's visual observations should evolve under its predicted motion. Generative world-action models (WAMs) jointly predict future observations and actions, yet existing WAMs for continuous VLN do not condition joint future-view and action generation on geometry-aware representations inferred from the observed history. We present WNM-3D, a generative World Navigation Model with 3D scene conditioning for continuous VLN. To consolidate past observations into persistent scene context, a frozen feed-forward geometry encoder extracts geometry-aware representations from the monocular egocentric RGB history, and a trainable 3D Scene-to-Token Adapter converts them into a fixed-length prefix in the token space of the world-action Diffusion Transformer. Through block-causal attention, this prefix conditions every future video-action block, providing a shared geometric context for both future-view and action generation. We train WNM-3D through supervised world-action fine-tuning on A*-generated demonstrations, DAgger-style adaptation on policy-visited states, and Counterfactual DanceGRPO refinement for closed-loop execution. Experiments on GN-Bench show that WNM-3D outperforms strong VLM-based navigation policies and its 2D-conditioned counterpart in closed-loop navigation. Stage-wise ablations further show that DAgger-SFT provides the larger success-rate gain, while Counterfactual DanceGRPO subsequently improves both navigation success and path efficiency.