# 3D-Belief: Embodied Belief Inference via Generative 3D World Modeling

arXiv: https://arxiv.org/abs/2605.11367 · HTML: https://mlsanity.com/paper/2605.11367/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Video-generation world models and simulators, one of 11 directions in World models.
- Builds on 30 of its 65 references that are in the map.
- First posted on arXiv 12 May 2026.

## Placed in

- World models / [Video-generation world models and simulators](https://mlsanity.com/wm/video-generation-world-models-and-simulators/)

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

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [AI2-THOR: An Interactive 3D Environment for Visual AI](https://mlsanity.com/paper/1712.05474/) (2017)
- [ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis](https://mlsanity.com/paper/2409.02048/) (2024)
- [No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images](https://mlsanity.com/paper/2410.24207/) (2024)
- [Stereo Magnification: Learning View Synthesis using Multiplane Images](https://mlsanity.com/paper/1805.09817/) (2018)
- [RoboDreamer: Learning Compositional World Models for Robot Imagination](https://mlsanity.com/paper/2404.12377/) (2024)
- [Stable Virtual Camera: Generative View Synthesis with Diffusion Models](https://mlsanity.com/paper/2503.14489/) (2025)
- [History-Guided Video Diffusion](https://mlsanity.com/paper/2502.06764/) (2025)
- [WorldMem: Long-term Consistent World Simulation with Memory](https://mlsanity.com/paper/2504.12369/) (2025)
- [Video Language Planning](https://mlsanity.com/paper/2310.10625/) (2023)
- [Streaming 4D Visual Geometry Transformer](https://mlsanity.com/paper/2507.11539/) (2025)
- [Training Agents Inside of Scalable World Models](https://mlsanity.com/paper/2509.24527/) (2025)
- [TrajectoryCrafter: Redirecting Camera Trajectory for Monocular Videos via Diffusion Models](https://mlsanity.com/paper/2503.05638/) (2025)
- [Rapid Exploration for Open-World Navigation with Latent Goal Models](https://mlsanity.com/paper/2104.05859/) (2021)
- [Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling](https://mlsanity.com/paper/2507.07982/) (2025)
- [TesserAct: Learning 4D Embodied World Models](https://mlsanity.com/paper/2504.20995/) (2025)
- [Simpler Diffusion (SiD2): 1.5 FID on ImageNet512 with pixel-space diffusion](https://mlsanity.com/paper/2410.19324/) (2024)
- [MindJourney: Test-Time Scaling with World Models for Spatial Reasoning](https://mlsanity.com/paper/2507.12508/) (2025)
- [COMBO: Compositional World Models for Embodied Multi-Agent Cooperation](https://mlsanity.com/paper/2404.10775/) (2024)
- [Feature Splatting: Language-Driven Physics-Based Scene Synthesis and Editing](https://mlsanity.com/paper/2404.01223/) (2024)
- [Lyra 2.0: Explorable Generative 3D Worlds](https://mlsanity.com/paper/2604.13036/) (2026)
- [FlashWorld: High-quality 3D Scene Generation within Seconds](https://mlsanity.com/paper/2510.13678/) (2025)
- [Video Diffusion Models: A Survey](https://mlsanity.com/paper/2405.03150/) (2024)
- [Learning 3D Persistent Embodied World Models](https://mlsanity.com/paper/2505.05495/) (2025)
- [Selective Visual Representations Improve Convergence and Generalization for Embodied AI](https://mlsanity.com/paper/2311.04193/) (2023)
- [WorldPack: Dynamic Frame Compression for Long-context Video World Modeling](https://mlsanity.com/paper/2512.02473/) (2025)
- [Rein3D: Reinforced 3D Indoor Scene Generation with Panoramic Video Diffusion Models](https://mlsanity.com/paper/2604.10578/) (2026)
- [SemGS: Feed-Forward Semantic 3D Gaussian Splatting from Sparse Views for Generalizable Scene Understanding](https://mlsanity.com/paper/2603.02548/) (2026)

## Built on by (most cited first, 1 of 1)

- [JEPA-TTT: Persistent Test-Time Training of Latent World Models for Planning under Dynamics Shifts](https://mlsanity.com/paper/2610.00722/) (2026)

## Abstract (arXiv)

Recent advances in visual generative models have highlighted the promise of learning generative world models. However, most existing approaches frame world modeling as novel-view synthesis or future-frame prediction, emphasizing visual realism rather than the structured uncertainty required by embodied agents acting under partial observability. In this work, we propose a different perspective: world modeling as embodied belief inference in 3D space. From this view, a world model should not merely render what may be seen, but maintain and update an agent's belief about the unobserved 3D world as new observations are acquired. We identify several key capabilities for such models, including spatially consistent scene memory, multi-hypothesis belief sampling, sequential belief updating, and semantically informed prediction of unseen regions. We instantiate these ideas in 3D-Belief, a generative 3D world model that infers explicit, actionable 3D beliefs from partial observations and updates them online over time. Unlike prior visual prediction models, 3D-Belief represents uncertainty directly in 3D, enabling embodied agents to imagine plausible scene completions and reason over partially observed environments. We evaluate 3D-Belief on 2D visual quality for scene memory and unobserved-scene imagination, object- and scene-level 3D imagination using our proposed 3D-CORE benchmark, and challenging object navigation tasks in both simulation and the real world. Experiments show that 3D-Belief improves 2D and 3D imagination quality and downstream embodied task performance compared to state-of-the-art methods.