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.
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.
New research reveals that transparency around how artificial intelligence obscures sensitive information is crucial for fostering user confidence in AI-driven communication.
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.
![A robot, guided by an action-conditioned world model, demonstrates a capacity for sustained, structurally-consistent video prediction-maintaining the integrity of a simulated object [latex] \text{over time} [/latex]-where competing methods rapidly succumb to accumulating error and object disintegration, establishing a new benchmark in predictive fidelity.](https://arxiv.org/html/2603.25685v1/x1.png)
Researchers are leveraging reinforcement learning to refine simulated environments, creating more reliable and consistent ‘world models’ for training and evaluating robotic systems.
![A symmetry-aware machine learning model’s predictive accuracy hinges on its adherence to group equivariance-specifically, whether its outputs transform predictably under symmetry operations-a condition quantified by metrics assessing both the variance of back-transformed predictions [latex]A_{\alpha}[/latex] and the decomposition of internal features [latex]B_{\alpha}[/latex] using Haar integration over the relevant symmetry group.](https://arxiv.org/html/2603.24638v1/x1.png)
New research reveals that machine learning models can independently learn fundamental physical symmetries, offering insights into their internal representations and the impact of neural network design.
A new framework leverages artificial intelligence to drastically reduce the time and effort required to prepare input files for nuclear reactor modeling.