Researchers have developed a novel framework that allows robotic agents to learn complex manipulation tasks from a single video demonstration, bridging the gap between visual perception and skilled action.
This review explores how modern system identification techniques are moving beyond pure prediction to prioritize control-relevant properties like stability and physical plausibility.
Researchers have developed a new reinforcement learning system that enables humanoid robots to reliably and accurately kick a soccer ball, even with imperfect sensor data.
A new analysis charts the rapid progression of artificial intelligence in cybersecurity, examining how systems are moving beyond simple reasoning to fully automated threat response.
New research details a data-driven approach to understanding how moving objects interact, offering insights beyond traditional simulation methods.
A new approach to human-AI collaboration focuses on jointly constructing causal models of the world, rather than simply aligning behaviors.
Researchers are leveraging the power of spiking neural networks and reinforcement learning to create robots that can navigate complex social environments with improved adaptability and efficiency.
A new autonomous system leverages artificial intelligence to automatically identify, categorize, and report on marine life and objects, promising a significant leap forward for ocean research.
New research explores how giving robots distinct personalities, powered by large language models, impacts how humans interact with and perceive these machines.
A new study reveals that simple AI agents can reliably optimize biomedical imaging workflows, often surpassing the performance of human experts.