10 stories tagged World Models
Researchers introduced WM-R1, a new AI framework that trains mobile app agents using virtual worlds instead of real devices. This reduces costs and speeds up learning, potentially making AI assistants for apps more accessible.
Researchers introduced CG-World, a large-scale dataset derived from industrial computer graphics pipelines that explicitly records intermediate world states—including spatial structure, motion curves, physics caches, and contact events—to help AI models learn the joint dynamics of states, actions, events, and observations.
Researchers introduced DROPJ, a human-centered method that trains AI agents safely by combining world models with human feedback and justifications. This approach could make AI systems more reliable in safety-critical domains like healthcare and autonomous driving.
Researchers found that AI models designed to understand spatial relationships, like 'put the red block left of the blue block,' often rely on hidden clues in the instructions rather than actual perception. This discovery highlights a major flaw in how AI understands physical tasks.
Researchers compare two approaches to world models for AI agents—agent-based and parameterized—showing that parameterized models reduce hallucination propagation by using measurable errors, leading to more reliable planning in step-by-step tasks.
Odyssey, a startup developing world models for AI, has secured a $1.45 billion valuation with backing from Amazon and other major investors. This highlights the growing importance of world models as the next big advancement beyond traditional language models.
Scientists found that AI models often predict realistic-looking but physically impossible outcomes. They propose a new approach that focuses on understanding real-world physics to make AI more reliable.
Runway, originally a tool for filmmakers, is now focusing on AI video generation to compete with tech giants like Google. The company believes its outsider status gives it an edge in this rapidly evolving field.
Researchers have developed a new approach to help AI understand when actions are possible in changing environments. This could make AI more adaptable in real-world situations where conditions constantly shift.
Researchers propose a new way for AI to understand the world by combining physics with predictive models. This could make AI systems like robots and self-driving cars smarter and more adaptable.