A RootBot, a soft-growing robot inspired by plant roots, has been developed for the high-curvature ground excavation. Its innovative design allows efficient steering and soil removal within constrained spaces. RootBot is expected to bring a paradigm shift in landscapes of urban infrastructures and various engineering practices.   Biomimetics, the art of drawing innovation from nature's design, is evolving...

A research team at KAIST, led by Professor Sung-Ju Lee, proposed FedTherapist, a privacy-preserving smartphone mental health monitoring system that uses federated learning for continuous speech and keyboard input.       The research team led by Professor Sung-Ju Lee in the School of Electrical Engineering developed a technology named FedTherapist that automatically analyzes the language usage pat...

Researchers at KAIST and DGIST have developed programmable photonic circuits with extremely low power consumption and reconfiguration energy, based on microelectromechanical systems (MEMS) technologies.   Researchers at KAIST and DGIST in Korea have developed programmable photonic circuits with extremely low power consumption and reconfiguration energy, based on silicon photonics and microelectromechanica...

For sustainable manned missions to the Moon or Mars, a space habitation system or space shelter is essential to protect astronauts from various hazards. The origami-based space shelter enables efficient transportation by launch vehicle and rapid on-site installation, presenting a new framework for early space habitation.   With recent advancements in launch vehicle technology, the scope of space missions, ...

A novel laser-based technology can generate and distribute electronic clock signals within semiconductor chips with femtosecond (10-15 second) precision timing and low heat dissipation, which have been challenging to achieve with conventional approaches.   As the performance of semiconductor chips has improved dramatically in recent years, the need for more precise and accurate timing inside chips has also...

Diffusion models have shown remarkable performance in editing images. However, extending those capabilities to complex visuals such as videos or 3D scenes remains challenging. This work presents a unified approach that enables the editing of such complex visuals by leveraging diffusion models, marking a significant advancement in the field.   In the field of AI, text-to-image diffusion models represent a s...