Science

A new benchmark assesses the ability of large language models to function as coding agents within complex, existing scientific software projects.

A novel algorithm combines the efficiency of ant colony optimization with a structural prior to enable scalable and balanced path planning for multiple robots operating in complex environments.

A new benchmark reveals the challenges AI agents face when analyzing complex, real-world biological data from spatial transcriptomics.

A new framework empowers artificial intelligence to not only conduct experiments, but to autonomously discover and refine the goals of scientific inquiry itself.

A new approach leverages feature space rotation to enable generative models to quickly adapt to new datasets with limited examples.

New research reveals a stealthy technique for lateral movement in Operational Technology environments, allowing attackers to navigate between Programmable Logic Controllers without triggering traditional security alerts.

A new approach combats popularity bias in recommender systems, improving the relevance and variety of suggestions users receive.

A new approach allows teams of agents to coordinate effectively even when they have differing understandings of the world.

A new approach combines system identification with reinforcement learning to achieve efficient and accurate control of complex dynamics.

Researchers have developed a novel, tuning-free method that significantly improves the quality and coherence of images restored with text prompts.