Interactive World Simulation with Cosmos for Physical AI
cs.AI, cs.CV, cs.LG, cs.RO
Submitted: 2026-11-04
Updated: 2026-11-04
Code: https://github.com/nvidia/cosmos
Project page: https://nv-tlabs.github.io/Project-Lyra
Terminology
Sources
- V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
- Qwen3-VL Technical Report
- NVIDIA OmniDreams: Real-Time Generative World Model for Closed-Loop Autonomous Vehicle Simulation
- Demystifying MMD GANs
- Into the LidarVerse: A Real-Time Unified LiDAR World Model Across Tasks and Sensors
- LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation
- M$^\text{4}$World: A Multi-view Multimodal Driving World Model for Interactive Object Manipulation and Minute-long Streaming
- Emerging Properties in Unified Multimodal Pretraining
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- Vidarc: Embodied Video Diffusion Model for Closed-loop Control
- Infinite Worlds with Versatile Interactions
- Unified 4D World Action Modeling from Video Priors with Asynchronous Denoising
- PROWL: Prioritized Regret-Driven Optimization for World Model Learning
- World Models
- ZYT-World: A Real-Time Controllable World Model for Closed-Loop Autonomous-Driving Simulation
- LoRA: Low-Rank Adaptation of Large Language Models
- ViPE: Video Pose Engine for 3D Geometric Perception
- Wan-Streamer v0.2: Higher Resolution, Same Latency
- Learning Transferable Dynamics Priors from Action to World Modeling
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents