# VRAG: Learning World Models for Interactive Video Generation

arXiv: https://arxiv.org/abs/2505.21996 · HTML: https://mlsanity.com/paper/2505.21996/

## Key facts

- Cited by 38 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 58 of its 66 references that are in the map.
- First posted on arXiv 28 May 2025.

## Placed in

- World models / [Video-generation world models and simulators](https://mlsanity.com/wm/video-generation-world-models-and-simulators/)
- Retrieval-augmented generation / [Multimodal RAG](https://mlsanity.com/rag/multimodal-rag/)

## Builds on (most cited first, 30 of 58)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Generative Modeling by Estimating Gradients of the Data Distribution](https://mlsanity.com/paper/1907.05600/) (2019)
- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [Video Diffusion Models](https://mlsanity.com/paper/2204.03458/) (2022)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [Make-A-Video: Text-to-Video Generation without Text-Video Data](https://mlsanity.com/paper/2209.14792/) (2022)
- [Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2304.08818/) (2023)
- [Mastering Atari with Discrete World Models](https://mlsanity.com/paper/2010.02193/) (2020)
- [CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers](https://mlsanity.com/paper/2205.15868/) (2022)
- [Recurrent World Models Facilitate Policy Evolution](https://mlsanity.com/paper/1809.01999/) (2018)
- [Genie: Generative Interactive Environments](https://mlsanity.com/paper/2402.15391/) (2024)
- [Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion](https://mlsanity.com/paper/2407.01392/) (2024)
- [ModelScope Text-to-Video Technical Report](https://mlsanity.com/paper/2308.06571/) (2023)
- [Open-Sora: Democratizing Efficient Video Production for All](https://mlsanity.com/paper/2412.20404/) (2024)
- [GAIA-1: A Generative World Model for Autonomous Driving](https://mlsanity.com/paper/2309.17080/) (2023)
- [YaRN: Efficient Context Window Extension of Large Language Models](https://mlsanity.com/paper/2309.00071/) (2023)
- [Structure and Content-Guided Video Synthesis with Diffusion Models](https://mlsanity.com/paper/2302.03011/) (2023)
- [VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models](https://mlsanity.com/paper/2401.09047/) (2024)
- [CAT3D: Create Anything in 3D with Multi-View Diffusion Models](https://mlsanity.com/paper/2405.10314/) (2024)

## Built on by (most cited first, 30 of 38)

- [WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling](https://mlsanity.com/paper/2512.14614/) (2025)
- [A Comprehensive Survey on World Models for Embodied AI](https://mlsanity.com/paper/2510.16732/) (2025)
- [Memory Forcing: Spatio-Temporal Memory for Consistent Scene Generation on Minecraft](https://mlsanity.com/paper/2510.03198/) (2025)
- [MemFlow: Flowing Adaptive Memory for Consistent and Efficient Long Video Narratives](https://mlsanity.com/paper/2512.14699/) (2025)
- [MobileWorldBench: Towards Semantic World Modeling For Mobile Agents](https://mlsanity.com/paper/2512.14014/) (2025)
- [MBench: A Comprehensive Benchmark on Memory Capability for Video World Models](https://mlsanity.com/paper/2606.00793/) (2026)
- [AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories](https://mlsanity.com/paper/2602.14941/) (2026)
- [Addressable Memory for Video World Models](https://mlsanity.com/paper/2608.07408/) (2026)
- [Code World Model: Coding Agent as World Brain](https://mlsanity.com/paper/2608.25927/) (2026)
- [WorldCam: Interactive Autoregressive 3D Gaming Worlds with Camera Pose as a Unifying Geometric Representation](https://mlsanity.com/paper/2603.16871/) (2026)
- [Recurrent Autoregressive Diffusion: Global Memory Meets Local Attention](https://mlsanity.com/paper/2511.12940/) (2025)
- [LongVie 2: Multimodal Controllable Ultra-Long Video World Model](https://mlsanity.com/paper/2512.13604/) (2025)
- [Plenoptic Video Generation](https://mlsanity.com/paper/2601.05239/) (2026)
- [MemLearner: Learning to Query Context memory for Video World Models](https://mlsanity.com/paper/2606.31734/) (2026)
- [Seeing Is Believing? A Benchmark for Multimodal Large Language Models on Visual Illusions and Anomalies](https://mlsanity.com/paper/2602.01816/) (2026)
- [NovaPlan: Zero-Shot Long-Horizon Manipulation via Closed-Loop Video Language Planning](https://mlsanity.com/paper/2602.20119/) (2026)
- [What-If World: A Causal Benchmark for General World Models in Embodied Scenarios](https://mlsanity.com/paper/2605.27589/) (2026)
- [Towards Interactive Video World Modeling: Frontiers, Challenges, Benchmarks, and Future Trends](https://mlsanity.com/paper/2606.01164/) (2026)
- [A Mechanistic View on Video Generation as World Models: State and Dynamics](https://mlsanity.com/paper/2601.17067/) (2026)
- [Echo-Memory: A Controlled Study of Memory in Action World Models](https://mlsanity.com/paper/2606.09803/) (2026)
- [Directing the World: Fast Autoregressive Video Generation with Compositional Human-Camera Control](https://mlsanity.com/paper/2606.27964/) (2026)
- [SPIRAL: Self-Evolving Action-Conditioned Video Generation via Reflective Planning Agents](https://mlsanity.com/paper/2603.08403/) (2026)
- [Video4Spatial: Towards Visuospatial Intelligence with Context-Guided Video Generation](https://mlsanity.com/paper/2512.03040/) (2025)
- [Understanding Rollout Error in Graph World Models](https://mlsanity.com/paper/2606.27780/) (2026)
- [WorldCycle: Self-Verifiable Reinforcement Learning for Long-Horizon Video World Models](https://mlsanity.com/paper/2608.04964/) (2026)
- [World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks](https://mlsanity.com/paper/2605.19957/) (2026)
- [DecMem: Towards Minute-Long Consistent World Generation with Decoupled Memory](https://mlsanity.com/paper/2605.31336/) (2026)
- [Retrieve What's Missing: Coverage-Maximizing Retrieval for Consistent Long Video Generation](https://mlsanity.com/paper/2606.02479/) (2026)
- [PhysEditWorld: A Large-Scale Dataset Toward Physics-Editable World Models](https://mlsanity.com/paper/2606.26694/) (2026)
- [MCP-Cosmos: World Model-Augmented Agents for Complex Task Execution in MCP Environments](https://mlsanity.com/paper/2605.09131/) (2026)

## Abstract (arXiv)

Foundational world models must be both interactive and preserve spatiotemporal coherence for effective future planning with action choices. However, present models for long video generation have limited inherent world modeling capabilities due to two main challenges: compounding errors and insufficient memory mechanisms. We enhance image-to-video models with interactive capabilities through additional action conditioning and autoregressive framework, and reveal that compounding error is inherently irreducible in autoregressive video generation, while insufficient memory mechanism leads to incoherence of world models. We propose video retrieval augmented generation (VRAG) with explicit global state conditioning, which significantly reduces long-term compounding errors and increases spatiotemporal consistency of world models. In contrast, naive autoregressive generation with extended context windows and retrieval-augmented generation prove less effective for video generation, primarily due to the limited in-context learning capabilities of current video models. Our work illuminates the fundamental challenges in video world models and establishes a comprehensive benchmark for improving video generation models with internal world modeling capabilities.