# DreamWorld: Unified World Modeling in Video Generation

arXiv: https://arxiv.org/abs/2603.00466 · HTML: https://mlsanity.com/paper/2603.00466/

## Key facts

- Cited by 7 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 29 of its 42 references that are in the map.
- First posted on arXiv 28 Feb 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, 29 of 29)

- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning](https://mlsanity.com/paper/2506.09985/) (2025)
- [Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think](https://mlsanity.com/paper/2410.06940/) (2024)
- [Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion](https://mlsanity.com/paper/2407.01392/) (2024)
- [Latte: Latent Diffusion Transformer for Video Generation](https://mlsanity.com/paper/2401.03048/) (2024)
- [Revisiting Feature Prediction for Learning Visual Representations from Video](https://mlsanity.com/paper/2404.08471/) (2024)
- [Lumiere: A Space-Time Diffusion Model for Video Generation](https://mlsanity.com/paper/2401.12945/) (2024)
- [Pyramidal Flow Matching for Efficient Video Generative Modeling](https://mlsanity.com/paper/2410.05954/) (2024)
- [VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness](https://mlsanity.com/paper/2503.21755/) (2025)
- [LTX-2: Efficient Joint Audio-Visual Foundation Model](https://mlsanity.com/paper/2601.03233/) (2026)
- [How Far is Video Generation from World Model: A Physical Law Perspective](https://mlsanity.com/paper/2411.02385/) (2024)
- [Cyclical Annealing Schedule: A Simple Approach to Mitigating KL Vanishing](https://mlsanity.com/paper/1903.10145/) (2019)
- [Video World Models with Long-term Spatial Memory](https://mlsanity.com/paper/2506.05284/) (2025)
- [VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion Generation in Video Models](https://mlsanity.com/paper/2502.02492/) (2025)
- [VideoREPA: Learning Physics for Video Generation through Relational Alignment with Foundation Models](https://mlsanity.com/paper/2505.23656/) (2025)
- [Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling](https://mlsanity.com/paper/2507.07982/) (2025)
- [DriveWorld: 4D Pre-trained Scene Understanding via World Models for Autonomous Driving](https://mlsanity.com/paper/2405.04390/) (2024)
- [No Other Representation Component Is Needed: Diffusion Transformers Can Provide Representation Guidance by Themselves](https://mlsanity.com/paper/2505.02831/) (2025)
- [Boosting Generative Image Modeling via Joint Image-Feature Synthesis](https://mlsanity.com/paper/2504.16064/) (2025)
- [Thinking with Video: Video Generation as a Promising Multimodal Reasoning Paradigm](https://mlsanity.com/paper/2511.04570/) (2025)
- [Aligning Text to Image in Diffusion Models is Easier Than You Think](https://mlsanity.com/paper/2503.08250/) (2025)
- [MaskFlow: Discrete Flows For Flexible and Efficient Long Video Generation](https://mlsanity.com/paper/2502.11234/) (2025)
- [Guiding Cross-Modal Representations with MLLM Priors via Preference Alignment](https://mlsanity.com/paper/2506.06970/) (2025)
- [AlignVid: Training-Free Attention Scaling for Semantic Fidelity in Text-Guided Image-to-Video Generation](https://mlsanity.com/paper/2512.01334/) (2025)
- [Semantic-Space-Intervened Diffusive Alignment for Visual Classification](https://mlsanity.com/paper/2505.05721/) (2025)
- [Multi-dimensional Preference Alignment by Conditioning Reward Itself](https://mlsanity.com/paper/2512.10237/) (2025)

## Built on by (most cited first, 7 of 7)

- [DreamWAM: Beyond RGB Future Prediction for World Action Models](https://mlsanity.com/paper/2608.04996/) (2026)
- [VideoWeave: Unlocking Geometric Consistency in Video Generation via Joint Geometry-Video Modeling](https://mlsanity.com/paper/2606.14162/) (2026)
- [LaMo: Self-Supervised Latent Motion Priors for Physical Realism in Video Generation](https://mlsanity.com/paper/2605.23878/) (2026)
- [UniVR: Thinking in Visual Space for Unified Visual Reasoning](https://mlsanity.com/paper/2607.12800/) (2026)
- [STRIKE: Learning Visual State Transitions for Physical World Modeling](https://mlsanity.com/paper/2610.09514/) (2026)
- [IntactWorld: Joint World Modeling with Intact Features](https://mlsanity.com/paper/2610.11174/) (2026)
- [What Visual Representations Do World Action Models Need?](https://mlsanity.com/paper/2610.13024/) (2026)

## Abstract (arXiv)

Despite impressive progress in video generation, existing models remain limited to surface-level plausibility, lacking a coherent and unified understanding of the world. Prior approaches typically incorporate only a single form of world-related knowledge or rely on rigid alignment strategies to introduce additional knowledge. However, aligning the single world knowledge is insufficient to constitute a world model that requires jointly modeling multiple heterogeneous dimensions (e.g., physical commonsense, 3D and temporal consistency). To address this limitation, we introduce DreamWorld, a unified framework that integrates complementary world knowledge into video generators via a Joint World Modeling Paradigm, jointly predicting video pixels and features from foundation models to capture temporal dynamics, spatial geometry, and semantic consistency. However, naively optimizing these heterogeneous objectives can lead to visual instability and temporal flickering. To mitigate this issue, we propose textitConsistent Constraint Annealing (CCA) to progressively regulate world-level constraints during training, and textitMulti-Source Inner-Guidance to enforce learned world priors at inference. Extensive evaluations show that DreamWorld improves world consistency, outperforming Wan2.1 by 2.26 points on VBench. Code will be made publicly available at hrefhttps://github.com/ABU121111/DreamWorldtextcolormypinkGithub.