Naver said 23 papers from its technology organisations, including Naver Labs, Naver Labs Europe, Naver AI Lab and Naver Cloud, were accepted as regular papers at ECCV 2026. Four were selected for ECCV Spotlight, awarded to about 1 to 2 percent of submissions. The accepted research spans 3D perception and reconstruction, vision AI models and robot driving simulation, including work on SLAM, indoor 3D generation from a single panorama, and a city-scale model developed with KAIST.

Researchers in South Korea have developed techniques to reduce cases in which AI confuses multiple sensory inputs or generates nonexistent information. KAIST said a team led by professor Yong-man Ro developed two methods to improve sensor understanding in multimodal large language models and reduce confusion between visual and audio data. The approaches are designed to work with less data or be applied without retraining. KAIST said the technology could be used in autonomous driving, rescue robots, drones and medical AI.