Researchers have developed a powerful new simulation framework that brings full-body musculoskeletal movement learning to life, paving the way for more realistic and adaptable embodied AI.
Researchers are replacing traditional genetic algorithms with AI agents capable of independently optimizing complex code, pushing the boundaries of automated software development.
Researchers have demonstrated that an AI agent assisted with external metacognitive feedback consistently outperforms those relying solely on self-assessment in complex engineering design tasks.
Researchers are tackling the challenge of creating robotic systems that can consistently and reliably play complex tabletop games alongside humans.
New advances in hyperspectral imaging are enabling more accurate environmental perception for autonomous vehicles, paving the way for safer and more reliable self-driving systems.
![The system dissects a hardware design [latex]\mathcal{D}[/latex] into its functional components, deploying a swarm of optimizer agents-each focused on a sub-function-to explore performance trade-offs between latency and area, then leverages integer linear programming to identify top-performing combinations before subjecting them to further, iterative refinement by exploration agents, ultimately yielding a fully optimized design [latex]\mathcal{D}^{\ast}[/latex].](https://arxiv.org/html/2603.25719v1/x1.png)
A new approach uses teams of AI-powered agents to automatically optimize hardware designs, pushing the boundaries of performance and efficiency.
![Despite a consistent central tendency across iterations of the federated learning process, client-specific performance-measured by [latex]BA[/latex]-exhibits substantial variability in its range and susceptibility to outlier values, suggesting inherent instability within the distributed system.](https://arxiv.org/html/2603.24601v1/imgs/boxplot_exp-BA.png)
Researchers are combining the strengths of centralized and federated learning with Transformer models to build more accurate and privacy-preserving human activity recognition systems.
A new framework dynamically adjusts how artificial intelligence processes information, significantly reducing its power consumption without compromising performance.
Researchers have developed a new framework that allows robots to grasp entire visual scenes from minimal information, paving the way for more robust and efficient learning.
New research reveals that transparency around how artificial intelligence obscures sensitive information is crucial for fostering user confidence in AI-driven communication.