NVIDIA OmniDreams: Real-Time Generative World Model for Closed-Loop Autonomous Vehicle Simulation

arXiv:2606.03159 · cs.CV, cs.AI, cs.RO · Submitted 2026-06-02 · Read on arXiv

cs.CV, cs.AI, cs.RO

Submitted: 2026-06-02

Updated: 2026-09-23

Code: https://github.com/ModelTC/lightx2v

Terminology

• World Model — 76× in this paper · explained in 7 episodes
• Distillation — 22× in this paper · explained in 2 episodes
• KV cache — 22× in this paper · explained in 3 episodes
• Consistency — 14× in this paper · explained in 3 episodes
• Foundation Model — 8× in this paper · explained in 3 episodes
• Transformer — 8× in this paper · explained in 2 episodes
• Diffusion Model — 7× in this paper · explained in 8 episodes
• World-Action Model — 7× in this paper
• Distribution Matching — 6× in this paper · explained in 2 episodes
• Fidelity — 6× in this paper · explained in 2 episodes
• Actor — 5× in this paper · explained in 3 episodes
• Conference on Computer Vision and Pattern Recognition — 5× in this paper
• Diffusion Models — 5× in this paper · explained in 6 episodes
• Flow Matching — 5× in this paper · explained in 8 episodes
• Gaussian Splatting — 5× in this paper · explained in 4 episodes
• 3D Gaussian Splatting — 4× in this paper · explained in 2 episodes
• Distribution Matching Distillation — 4× in this paper
• Temporal consistency — 4× in this paper · explained in 2 episodes
• Adaptation — 3× in this paper · explained in 1 episode
• Core — 3× in this paper · explained in 2 episodes
• Decode — 3× in this paper · explained in 2 episodes
• Embeddings — 3× in this paper · explained in 2 episodes
• Exposure Bias — 3× in this paper · explained in 2 episodes
• Foundation Models — 3× in this paper · explained in 7 episodes
• Generative Model — 3× in this paper · explained in 2 episodes
• In International Conference on Learning Representations — 3× in this paper
• Adam — 2× in this paper · explained in 2 episodes
• Benchmark — 2× in this paper · explained in 2 episodes
• Closed-Loop System — 2× in this paper · explained in 4 episodes
• Diffusion Process — 2× in this paper · explained in 2 episodes
• Rectified Flow — 2× in this paper · explained in 3 episodes
• Sparse Attention — 2× in this paper · explained in 5 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Agent Interactions — 1× in this paper · explained in 1 episode
• Computational overhead — 1× in this paper · explained in 2 episodes
• Distribution Shift — 1× in this paper · explained in 6 episodes
• Elias — 1× in this paper · explained in 2 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Generative Models — 1× in this paper · explained in 2 episodes
• Gradient Flow — 1× in this paper · explained in 2 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• Iterative Refinement — 1× in this paper · explained in 3 episodes
• Joint Attention — 1× in this paper · explained in 2 episodes
• Latent Representation — 1× in this paper · explained in 2 episodes
• Latent Space — 1× in this paper · explained in 7 episodes
• Modularity — 1× in this paper · explained in 9 episodes
• Optical Flow — 1× in this paper · explained in 2 episodes
• Real Driving Scene — 1× in this paper
• Reasoning Traces — 1× in this paper · explained in 3 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Steering — 1× in this paper · explained in 2 episodes
• Temporal Reasoning — 1× in this paper · explained in 2 episodes
• Trace — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• Cosmos World Foundation Model Platform for Physical AI
• Qwen Technical Report
• ArtiFixer: Enhancing and Extending 3D Reconstruction with Auto-Regressive Diffusion Models
• Flex Attention: A Programming Model for Generating Optimized Attention Kernels
• GAIA-1: A Generative World Model for Autonomous Driving
• Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion
• BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers
• Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow
• LATR: 3D Lane Detection from Monocular Images with Transformer
• World Simulation with Video Foundation Models for Physical AI
• Alpamayo-R1: Bridging Reasoning and Action Prediction for Generalizable Autonomous Driving in the Long Tail
• Movie Gen: A Cast of Media Foundation Models
• Cosmos-Drive-Dreams: Scalable Synthetic Driving Data Generation with World Foundation Models
• GAIA-2: A Controllable Multi-View Generative World Model for Autonomous Driving
• Advancing Open-source World Models
• Wan: Open and Advanced Large-Scale Video Generative Models
• ChronoEdit: Towards Temporal Reasoning for Image Editing and World Simulation
• DriveArena: A Closed-loop Generative Simulation Platform for Autonomous Driving
• World Action Models are Zero-shot Policies
• Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention

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