Researchers have developed a novel adaptive photomemristor architecture that mimics the dynamic range of the human eye, improving vision system performance in complex lighting.
The company is integrating heavy foundation models as a semantic safety net to help delivery robots interpret complex, high-stakes urban environments.
A new architectural framework enables mobile robots to store and retrieve semantic information about their environment using natural language queries.
The ATLAS navigation system utilizes synthetic data and probabilistic filtering to enable uncrewed ground vehicles to operate in contested environments without satellite signals.
A new diagnostic metric provides real-time monitoring of vision-language models by quantifying the grounding of generated text in visual inputs.
The startup is deploying computer vision models to transform unstructured surgical video into structured clinical reports, aiming to reduce administrative burdens for surgeons.
The coffee giant has ended its nine-month pilot of an automated inventory system, citing significant technical limitations in real-world retail environments.
A new open-source dataset of one million synthetic charts enables smaller AI models to outperform larger commercial systems in complex visual data tasks.
Researchers from Penn State and Loughborough University have developed an image analysis method that maps the physical application of paint into quantifiable data.
Concordia University researchers utilized generative AI synthetic data to train a deep reinforcement learning agent capable of executing complex cardiac imaging without manual guidance.
Applied machine learning, filed daily.
Model releases, silicon, clinical deployment, and the policy shaping them. No digest padding.