DreamWorld: Unified World Modeling in Video Generation

arXiv:2603.00466 · cs.CV · Submitted 2026-02-28 · Read on arXiv

cs.CV

Submitted: 2026-02-28

Updated: 2026-10-12

Code: https://github.com/genmoai/models

Terminology

• Consistency — 3× in this paper · explained in 3 episodes
• Alignment — 1× in this paper · explained in 1 episode
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Temporal consistency — 1× in this paper · explained in 2 episodes
• Unified Framework — 1× in this paper · explained in 5 episodes
• World Model — 1× in this paper · explained in 7 episodes

Sources

• V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
• VideoPhy: Evaluating Physical Commonsense for Video Generation
• Lumiere: A Space-Time Diffusion Model for Video Generation
• Revisiting Feature Prediction for Learning Visual Representations from Video
• MoAlign: Motion-Centric Representation Alignment for Video Diffusion Models
• Genie: Generative Interactive Environments
• VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion Generation in Video Models
• Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion
• LTX-2: Efficient Joint Audio-Visual Foundation Model
• Classifier-Free Diffusion Guidance
• Multi-dimensional Preference Alignment by Conditioning Reward Itself
• No Other Representation Component Is Needed: Diffusion Transformers Can Provide Representation Guidance by Themselves
• Pyramidal Flow Matching for Efficient Video Generative Modeling
• How Far is Video Generation from World Model: A Physical Law Perspective
• HunyuanVideo: A Systematic Framework For Large Video Generative Models
• Boosting Generative Image Modeling via Joint Image-Feature Synthesis
• Aligning Text to Image in Diffusion Models is Easier Than You Think
• Semantic-Space-Intervened Diffusive Alignment for Visual Classification
• UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation
• Flow Matching for Generative Modeling

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models