Researchers are leveraging the power of generative artificial intelligence to automatically create realistic database workloads, accelerating the development and optimization of key database components.
Researchers have developed a system that uses artificial intelligence to translate descriptive scenes into dynamic actions for virtual agents, enabling procedurally generated interactive narratives.
A new framework combines the power of large language models with a multi-agent system to significantly improve the accuracy and flexibility of predicting outcomes in ongoing processes.
A new benchmark reveals that while large language models excel at following instructions, they struggle with the spatial awareness and social reasoning needed to navigate real-world interactions.
A new framework aims to shed light on how artificial intelligence models arrive at solutions for coding tasks, offering developers deeper insights into their behavior.
Researchers unveil TongSIM, a comprehensive environment for training and testing intelligent agents in realistic, multimodal scenarios.
A new benchmark reveals that vision-language models struggle with basic physical reasoning, often relying on memorization rather than genuine understanding of visual scenes.
A new framework enables robots to learn complex skills simply by observing videos, without needing explicit action labels.
A new approach called LieFlow learns underlying symmetries directly from data, offering a powerful way to analyze complex systems without pre-defined assumptions.
A new empirical study reveals how generative AI tools are impacting the daily workflows of software engineers.