# Lyra 2.0: Explorable Generative 3D Worlds

arXiv: https://arxiv.org/abs/2604.13036 · HTML: https://mlsanity.com/paper/2604.13036/

## Key facts

- Cited by 44 papers in the map (data through 14 Oct 2026).
- Builds on 131 of its 140 references that are in the map.
- First posted on arXiv 14 Apr 2026.

## Builds on (most cited first, 30 of 131)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [Zero-1-to-3: Zero-shot One Image to 3D Object](https://mlsanity.com/paper/2303.11328/) (2023)
- [Magic3D: High-Resolution Text-to-3D Content Creation](https://mlsanity.com/paper/2211.10440/) (2022)
- [ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation](https://mlsanity.com/paper/2305.16213/) (2023)
- [Efficient Geometry-aware 3D Generative Adversarial Networks](https://mlsanity.com/paper/2112.07945/) (2021)
- [One-step Diffusion with Distribution Matching Distillation](https://mlsanity.com/paper/2311.18828/) (2023)
- [MVDream: Multi-view Diffusion for 3D Generation](https://mlsanity.com/paper/2308.16512/) (2023)
- [WorldSimBench: Towards Video Generation Models as World Simulators](https://mlsanity.com/paper/2410.18072/) (2024)
- [Cosmos World Foundation Model Platform for Physical AI](https://mlsanity.com/paper/2501.03575/) (2025)
- [LRM: Large Reconstruction Model for Single Image to 3D](https://mlsanity.com/paper/2311.04400/) (2023)
- [LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation](https://mlsanity.com/paper/2402.05054/) (2024)
- [Depth Anything 3: Recovering the Visual Space from Any Views](https://mlsanity.com/paper/2511.10647/) (2025)
- [Wonder3D: Single Image to 3D using Cross-Domain Diffusion](https://mlsanity.com/paper/2310.15008/) (2023)
- [Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creation](https://mlsanity.com/paper/2303.13873/) (2023)
- [pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction](https://mlsanity.com/paper/2312.12337/) (2023)
- [SyncDreamer: Generating Multiview-consistent Images from a Single-view Image](https://mlsanity.com/paper/2309.03453/) (2023)
- [Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion](https://mlsanity.com/paper/2506.08009/) (2025)
- [Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation](https://mlsanity.com/paper/2212.00774/) (2022)
- [MotionCtrl: A Unified and Flexible Motion Controller for Video Generation](https://mlsanity.com/paper/2312.03641/) (2023)
- [DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision](https://mlsanity.com/paper/2312.16256/) (2023)
- [Zero-Shot Text-Guided Object Generation with Dream Fields](https://mlsanity.com/paper/2112.01455/) (2021)
- [CameraCtrl: Enabling Camera Control for Text-to-Video Generation](https://mlsanity.com/paper/2404.02101/) (2024)
- [UniPC: A Unified Predictor-Corrector Framework for Fast Sampling of Diffusion Models](https://mlsanity.com/paper/2302.04867/) (2023)
- [GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Images](https://mlsanity.com/paper/2209.11163/) (2022)

## Built on by (most cited first, 30 of 44)

- [Cosmos 3: Omnimodal World Models for Physical AI](https://mlsanity.com/paper/2606.02800/) (2026)
- [WorldMark: A Unified Benchmark Suite for Interactive Video World Models](https://mlsanity.com/paper/2604.21686/) (2026)
- [WAM4D: Fast 4D World Action Model via Spatial Register Tokens](https://mlsanity.com/paper/2606.14048/) (2026)
- [Alaya-EVOKE: From Linear-Scaling Supervision to Endless World](https://mlsanity.com/paper/2608.13546/) (2026)
- [EchoWM: Open and Enterable Omnimodal World Models](https://mlsanity.com/paper/2608.23189/) (2026)
- [WorldRoamBench: An Open-World Benchmark for Long-Horizon Stability of Interactive World Models](https://mlsanity.com/paper/2606.31672/) (2026)
- [Towards Interactive Video World Modeling: Frontiers, Challenges, Benchmarks, and Future Trends](https://mlsanity.com/paper/2606.01164/) (2026)
- [AlayaWorld: Long-Horizon and Playable Video World Generation](https://mlsanity.com/paper/2607.06291/) (2026)
- [StatePlay: State-Aware Game World Models for Mechanics-Consistent Generation](https://mlsanity.com/paper/2607.26754/) (2026)
- [Nano World Models: A Minimalist Implementation of Future Video Prediction](https://mlsanity.com/paper/2605.23993/) (2026)
- [Context-Matched Distillation: Teacher Causality for Autoregressive Video Distillation](https://mlsanity.com/paper/2608.13391/) (2026)
- [MoVerse: Real-Time Video World Modeling with Panoramic Gaussian Scaffold](https://mlsanity.com/paper/2606.13376/) (2026)
- [HarnessEval-W: Agentifying the Evaluation of Visual Worlds](https://mlsanity.com/paper/2608.16859/) (2026)
- [Long-Horizon Audio-Visual Generation for Persistent Stories and Interactive Worlds](https://mlsanity.com/paper/2608.23383/) (2026)
- [Holo-World: Unified Camera, Object and Weather Control for Video World Model](https://mlsanity.com/paper/2606.20083/) (2026)
- [OptiWorld: Optimal Control for Video World Generation under Physical Constraints](https://mlsanity.com/paper/2606.00499/) (2026)
- [3D-Belief: Embodied Belief Inference via Generative 3D World Modeling](https://mlsanity.com/paper/2605.11367/) (2026)
- [Feed-Forward Gaussian Splatting from Sparse Aerial Views](https://mlsanity.com/paper/2605.19949/) (2026)
- [MeRoPE: Metric Rotary Position Embedding for Camera-Controlled Video Generation](https://mlsanity.com/paper/2609.01252/) (2026)
- [WorldCrafter: Consistent Video World Model with Implicit 3D-aware Memory](https://mlsanity.com/paper/2609.24984/) (2026)
- [GameDirector: Decoupling Gameplay Logic from Rendering for Player-Configurable Game World Models](https://mlsanity.com/paper/2609.25652/) (2026)
- [Precise Editing and Flexible Referencing for Interactable Worlds](https://mlsanity.com/paper/2609.34470/) (2026)
- [Remember to be Curious: Episodic Context and Persistent Worlds for 3D Exploration](https://mlsanity.com/paper/2605.22814/) (2026)
- [FLAT: Feedforward Latent Triangle Splatting for Geometrically Accurate Scene Generation](https://mlsanity.com/paper/2606.24876/) (2026)
- [From Generation to Simulation: How Far Are World Models from Being True Simulators?](https://mlsanity.com/paper/2608.23070/) (2026)
- [HappyWorld-Bench](https://mlsanity.com/paper/2609.24308/) (2026)
- [Code Plans, Diffusion Renders: Open-Ended Generative World Modeling](https://mlsanity.com/paper/2609.26458/) (2026)
- [Spackle: Completing Large View Single Image NVS with Adaptive Gaussians](https://mlsanity.com/paper/2609.30941/) (2026)
- [WorldWeave: Growing Persistent Geometric Worlds for Video Generation](https://mlsanity.com/paper/2609.34221/) (2026)
- [Geometry as Address: Routing Attention to Visual Memory for Long-Horizon Camera-Controlled Video Generation](https://mlsanity.com/paper/2609.34722/) (2026)

## Abstract (arXiv)

Recent advances in video generation enable a new paradigm for 3D scene creation: generating camera-controlled videos that simulate scene walkthroughs, then lifting them to 3D via feed-forward reconstruction techniques. This generative reconstruction approach combines the visual fidelity and creative capacity of video models with 3D outputs ready for real-time rendering and simulation. Scaling to large, complex environments requires 3D-consistent video generation over long camera trajectories with large viewpoint changes and location revisits, a setting where current video models degrade quickly. Existing methods for long-horizon generation are fundamentally limited by two forms of degradation: spatial forgetting and temporal drifting. As exploration proceeds, previously observed regions fall outside the model's temporal context, forcing the model to hallucinate structures when revisited. Meanwhile, autoregressive generation accumulates small synthesis errors over time, gradually distorting scene appearance and geometry. We present Lyra 2.0, a framework for generating persistent, explorable 3D worlds at scale. To address spatial forgetting, we maintain per-frame 3D geometry and use it solely for information routing -- retrieving relevant past frames and establishing dense correspondences with the target viewpoints -- while relying on the generative prior for appearance synthesis. To address temporal drifting, we train with self-augmented histories that expose the model to its own degraded outputs, teaching it to correct drift rather than propagate it. Together, these enable substantially longer and 3D-consistent video trajectories, which we leverage to fine-tune feed-forward reconstruction models that reliably recover high-quality 3D scenes.