mlsanityData to 14 Oct 2026

Magpie: Real-Time World Renderer for Interactive Games

arXiv 2608.27168 ↗First posted 27 Aug 2026cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

Modern game development relies heavily on conventional graphics pipelines. High-quality visual content requires modeling, material authoring, animation, lighting, effects, and runtime optimization, making asset production expensive and extending the development cycle of game prototypes. Recently, video foundation models are beginning to change film and video production, but games differ from linear media, they require not only continuous and realistic imagery, but also stable and reproducible gameplay rules, object states, and interaction outcomes. We present Magpie, a real-time generative world-rendering system for interactive games. Magpie separates gameplay execution from visual generation. Designers define scenes and rules in a game engine. At runtime, the Game Engine resolves player actions and maintains world state, while an independent Render Server generates visual output from white-box frames produced by the engine. Magpie provides a system-level implementation path for applying generative models to real-time game rendering. It preserves gameplay designability and reproducibility, and reduces the dependence of early game prototypes on complete visual assets.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 36 of its 46 references that are in the map. First posted on arXiv 27 Aug 2026.

Builds on

36 of 46 references.

References · 36

  1. 2025Wan: Open and Advanced Large-Scale Video Generative Modelscited by 2,708
  2. 2023One-step Diffusion with Distribution Matching Distillationcited by 1,019
  3. 2024Improved Distribution Matching Distillation for Fast Image Synthesiscited by 684
  4. 2025Mean Flows for One-step Generative Modelingcited by 561
  5. 2025LongLive: Real-time Interactive Long Video Generationcited by 265
  6. 2026LTX-2: Efficient Joint Audio-Visual Foundation Modelcited by 236
  7. 2025Matrix-game 2.0: An open-source real-time and streaming interactive world modelcited by 186
  8. 2025Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Controlcited by 185
  9. 2026Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generationcited by 184
  10. 2025WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modelingcited by 170
  11. 2025Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrievalcited by 163
  12. 2026Seedance 2.0: Advancing Video Generation for World Complexitycited by 160
24 more
  1. 2026Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memorycited by 100
  2. 2025RELIC: Interactive Video World Model with Long-Horizon Memorycited by 96
  3. 2025Large Scale Diffusion Distillation via Score-Regularized Continuous-Time Consistencycited by 86
  4. 2026Helios: Real Real-Time Long Video Generation Modelcited by 65
  5. 2026Causal Forcing++: Scalable Few-Step Autoregressive Diffusion Distillation for Real-Time Interactive Video Generationcited by 56
  6. 2026SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformercited by 55
  7. 2026Solaris: Building a Multiplayer Video World Model in Minecraftcited by 47
  8. 2026DreamX-World 1.0: A General-Purpose Interactive World Modelcited by 40
  9. 2026LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generationcited by 30
  10. 2026AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillationcited by 26
  11. 2026Quantization-Aware Distillation for NVFP4 Inference Accuracy Recoverycited by 22
  12. 2026Multiplayer Interactive World Models with Representation Autoencoderscited by 19
  13. 2026ABot-World-0: Infinite Interactive World Rollout on a Single Desktop GPUcited by 16
  14. 2026WorldKV: Efficient World Memory with World Retrieval and Compressioncited by 15
  15. 2026Wonder: Video World Model Done Bettercited by 15
  16. 2026ActWorld: From Explorable to Interactive World Model via Action-Aware Memorycited by 14
  17. 2026Video Generation Models are General-Purpose Vision Learnerscited by 14
  18. 2026SkyReels-V4: Multi-modal Video-Audio Generation, Inpainting and Editing modelcited by 12
  19. 2026WorldCam: Interactive Autoregressive 3D Gaming Worlds with Camera Pose as a Unifying Geometric Representationcited by 12
  20. 2026Coarse-to-Real: Generative Rendering for Populated Dynamic Scenescited by 9
  21. 2026Echo-Infinity: Learning Evolving Memory for Real-Time Infinite Video Generationcited by 9
  22. 2026UniVidX: A Unified Multimodal Framework for Versatile Video Generation via Diffusion Priorscited by 3
  23. 2026WanToFight: Real-Time Generative Game Engine for Multi-Player Combat Interactioncited by 3
  24. 2026MoWorld: A Flash World Modelcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.