Researchers introduce K-Search, a new GPU kernel optimization framework that uses co-evolving world models with LLMs to significantly improve performance over existing methods. The system achieves up to 14.3x performance gains on complex kernels by decoupling high-level planning from low-level implementation, addressing limitations of current automated optimization approaches.
Google is expanding Gemini AI to become a universal world model capable of making plans and simulating new experiences. This represents a significant advancement toward building comprehensive AI assistants that can understand and interact with complex real-world scenarios.
Genie 2 is introduced as a large-scale foundation world model designed to generate unlimited diverse training environments. This development aims to support the creation and training of future general AI agents by providing varied simulation scenarios.
Researchers developed Risk-aware World Model Predictive Control (RaWMPC), a new framework for autonomous driving that makes safe decisions without relying on expert demonstrations. The system uses a world model to predict consequences of multiple actions and selects low-risk options through explicit risk evaluation, showing superior performance in both normal and rare driving scenarios.
