Multimodal large language models (MLLMs), which process multiple types of sensory information, such as text, images and audio, at the same time, are rapidly expanding the range of applications for artificial intelligence (AI). However, in real-world environments, these models can misinterpret the physical characteristics of sensors, mistakenly identify objects or claim to hear sounds that are not actually present simply because a certain object appears in a video. These errors are known as hallucinations.

Queues at sports events can be very long, even at large venues with many entrance gates. To speed things up, Geelong Football Club recently introduced an "express lane" option for club members.

To improve pedestrian safety in urban areas, researchers are developing technologies that alert pedestrians to potential hazards via smartphones or earbuds. However, loud warning sounds and strong vibrations can induce stress, and repeated alerts may eventually be ignored. To address this challenge, the researchers proposed a method that uses auditory augmented reality, which overlays information onto environmental sounds through earbuds, to slightly modify the sound of an approaching vehicle and naturally draw attention to it.