# NuiWorld: Exploring a Scalable Framework for End-to-End Controllable World Generation

arXiv: https://arxiv.org/abs/2601.19048 · HTML: https://mlsanity.com/paper/2601.19048/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 41 references that are in the map.
- First posted on arXiv 27 Jan 2026.

## Builds on (most cited first, 27 of 27)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network](https://mlsanity.com/paper/1609.05158/) (2016)
- [Structured 3D Latents for Scalable and Versatile 3D Generation](https://mlsanity.com/paper/2412.01506/) (2024)
- [3DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Models](https://mlsanity.com/paper/2301.11445/) (2023)
- [Native and Compact Structured Latents for 3D Generation](https://mlsanity.com/paper/2512.14692/) (2025)
- [Sparc3D: Sparse Representation and Construction for High-Resolution 3D Shapes Modeling](https://mlsanity.com/paper/2505.14521/) (2025)
- [Learning to generate line drawings that convey geometry and semantics](https://mlsanity.com/paper/2203.12691/) (2022)
- [BlockFusion: Expandable 3D Scene Generation using Latent Tri-plane Extrapolation](https://mlsanity.com/paper/2401.17053/) (2024)
- [SparseFlex: High-Resolution and Arbitrary-Topology 3D Shape Modeling](https://mlsanity.com/paper/2503.21732/) (2025)
- [LT3SD: Latent Trees for 3D Scene Diffusion](https://mlsanity.com/paper/2409.08215/) (2024)
- [SemCity: Semantic Scene Generation with Triplane Diffusion](https://mlsanity.com/paper/2403.07773/) (2024)
- [Efficient Part-level 3D Object Generation via Dual Volume Packing](https://mlsanity.com/paper/2506.09980/) (2025)
- [Pyramid Diffusion for Fine 3D Large Scene Generation](https://mlsanity.com/paper/2311.12085/) (2023)
- [LATTICE: Democratize High-Fidelity 3D Generation at Scale](https://mlsanity.com/paper/2512.03052/) (2025)
- [AutoPartGen: Autogressive 3D Part Generation and Discovery](https://mlsanity.com/paper/2507.13346/) (2025)
- [SynCity: Training-Free Generation of 3D Worlds](https://mlsanity.com/paper/2503.16420/) (2025)
- [Unleashing Vecset Diffusion Model for Fast Shape Generation](https://mlsanity.com/paper/2503.16302/) (2025)
- [NuiScene: Exploring Efficient Generation of Unbounded Outdoor Scenes](https://mlsanity.com/paper/2503.16375/) (2025)
- [Yo'City: Personalized and Boundless 3D Realistic City Scene Generation via Self-Critic Expansion](https://mlsanity.com/paper/2511.18734/) (2025)
- [TRELLISWorld: Training-Free World Generation from Object Generators](https://mlsanity.com/paper/2510.23880/) (2025)
- [MajutsuCity: Language-driven Aesthetic-adaptive City Generation with Controllable 3D Assets and Layouts](https://mlsanity.com/paper/2511.20415/) (2025)
- [UrbanWorld2.0: A Multimodal Agentic Framework for Reality-Aligned 3D World Generation at City-Scale](https://mlsanity.com/paper/2511.18005/) (2025)

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

- [WorldClaw: Agentic 3D Open-World Generation at Scale](https://mlsanity.com/paper/2608.05248/) (2026)

## Abstract (arXiv)

World generation is a fundamental capability for applications like video games, simulation, and robotics. However, existing approaches face three main obstacles: controllability, scalability, and efficiency. End-to-end scene generation models have been limited by data scarcity. While object-centric generation approaches rely on fixed resolution representations, degrading fidelity for larger scenes. Training-free approaches, while flexible, are often slow and computationally expensive at inference time. We present NuiWorld, a framework that attempts to address these challenges. To overcome data scarcity, we propose a generative bootstrapping strategy that starts from a few input images. Leveraging recent 3D reconstruction and expandable scene generation techniques, we synthesize scenes of varying sizes and layouts, producing enough data to train an end-to-end model. Furthermore, our framework enables controllability through pseudo sketch labels, and demonstrates a degree of generalization to previously unseen sketches. Our approach represents scenes as a collection of variable scene chunks, which are compressed into a flattened vector-set representation. This significantly reduces the token length for large scenes, enabling consistent geometric fidelity across scenes sizes while improving training and inference efficiency.