Cosmos World Foundation Model Platform for Physical AI
Paper • 2501.03575 • Published • 84
World Model
-
-
Intuitive physics understanding emerges from self-supervised pretraining on natural videos
Paper • 2502.11831 • Published • 20 -
PhysicsGen: Can Generative Models Learn from Images to Predict Complex Physical Relations?
Paper • 2503.05333 • Published • 8 -
Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning
Paper • 2503.15558 • Published • 52 -
Cosmos-Transfer1: Conditional World Generation with Adaptive Multimodal Control
Paper • 2503.14492 • Published • 20 -
Exploring the Evolution of Physics Cognition in Video Generation: A Survey
Paper • 2503.21765 • Published • 11 -
WorldVLA: Towards Autoregressive Action World Model
Paper • 2506.21539 • Published • 40 -
World Action Models are Zero-shot Policies
Paper • 2602.15922 • Published • 20 -
ECHO: Terminal Agents Learn World Models for Free
Paper • 2605.24517 • Published • 8 -
NVIDIA OmniDreams: Real-Time Generative World Model for Closed-Loop Autonomous Vehicle Simulation
Paper • 2606.03159 • Published • 23 -
Cosmos 3: Omnimodal World Models for Physical AI
Paper • 2606.02800 • Published • 140 -
World Action Models: A Survey
Paper • 2606.20781 • Published • 56 -
Fast LeWorldModel
Paper • 2606.26217 • Published • 28