Extensive experimental results show that our method generalizes well for arbitrary groups ofclients and provides largeperformance improvements giventhe same overall communication/computation resources, compared to other baselines relying on knownpretrainingmethods.

LLM-based multi-agent simulations are a rapidly growing field of research, but current simulations often lack clear modes for interaction and analysis, limiting the "what if" scenarios researchers are able to investigate. In this demo, we define three core operations for interacting with multi-agent simulations: inject, fork, and compare. Inject allows researchers to introduce external events at any point during simulation execution. Fork creates independent timeline branches from any timestamp, preserving complete state while allowing divergent exploration. Compare facilitates parallel observation of multiple branches, revealing how different interventions lead to distinct emergent behaviors. Together, these operations establish a vocabulary that transforms linear simulation workflows into interactive, explorable spaces. We demonstrate this vocabulary through a commodity market simulation with fourteen AI agents, where researchers can inject contrasting events and observe divergent outcomes across parallel timelines. By defining these fundamental operations, we provide a starting point for systematic causal investigation in LLM-based agent simulations, moving beyond passive observation toward active experimentation.

It's Marvel, a four-legged robot that can quickly climb walls and walk across ceilings. The name stands for "magnetically adhesive robot for versatile and expeditious locomotion." One caveat: It only works on metal surfaces. A team of researchers from the Korea Advanced Institute of Science and Technology (KAIST) developed the robot and published a paper on its abilities in the journal Science Robotics last month. KAIST said it "climbs steel walls and crawls across metal ceilings at the fastest speed that the world has ever seen."

Recently, numerous studies have investigated cooperative traffic systems using the communication among vehicle-to-everything (V2X). Unfortunately, when multiple autonomous vehicles are deployed while exposed to communication failure, there might be a conflict of ideal conditions between various autonomous vehicles leading to adversarial situation on the roads. In South Korea, virtual and real-world urban autonomous multi-vehicle races were held in March and November of 2021, respectively. During the competition, multiple vehicles were involved simultaneously, which required maneuvers such as overtaking low-speed vehicles, negotiating intersections, and obeying traffic laws. In this study, we introduce a fully autonomous driving software stack to deploy a competitive driving model, which enabled us to win the urban autonomous multi-vehicle races. We evaluate module-based systems such as navigation, perception, and planning in real and virtual environments. Additionally, an analysis of traffic is performed after collecting multiple vehicle position data over communication to gain additional insight into a multi-agent autonomous driving scenario. Finally, we propose a method for analyzing traffic in order to compare the spatial distribution of multiple autonomous vehicles. We study the similarity distribution between each team's driving log data to determine the impact of competitive autonomous driving on the traffic environment.

Prof. Jong Chul Ye is a Professor of the Graduate School of AI and Affiliated Professor at Dept. of Bio/Brain Engineering and Dept. of Mathematical Sciences of Korea Advanced Institute of Science and Technology (KAIST), Korea. Before joining KAIST, he was a postdoctoral fellow at the University of Illinois at Urbana Champaign, a Senior Researcher at Philips Research at New York, and then GE Global Research in Niskayauna. He has served as an associate editor of IEEE Trans. He is currently an associate editor for IEEE Trans. He is an IEEE Fellow, and was the Chair of IEEE SPS Computational Imaging TC, and IEEE EMBS Distinguished Lecturer in 2021-2022.

Autonomous driving solutions are the next big thing in the transportation field. While many companies are bringing out autonomous driving solutions for passenger vehicles, not many are indulging in heavy motor vehicle autonomous driving solutions yet. Korean startup Mars Auto is dedicated to building self-driving trucks for commercial use. Self-driving truck technology is quite different from autonomous driving technology for urban passenger cars, and Mars Auto wants to make the technology commercial. Mars Auto develops artificial intelligence (AI)-based autonomous driving software for trucks for cargo transport.

It will house a dedicated GPU server farm, initially focusing on the development of artificial intelligence technology for robotics, medical and media.

This undated image, provided by KT Corp., shows its logo. KT Corp., a major South Korean telecom operator, said Sunday it signed an agreement with the country's top science and technology university to establish a research institute for artificial intelligence (AI) and software development. Under the agreement, KT will work with the Korea Advanced Institute of Science and Technology (KAIST) to build the research institute in the central city of Daejeon, 164 kilometers south of Seoul, by the end of this year. KT said the institute will house around 200 KAIST researchers, faculty members and KT employees to develop future technologies, including an AI model that can recognize complex situations based on voice and video recognition. The two will also conduct joint research in developing AI for industrial settings, such as in media, health care and robotics.

Researchers at the Korea Advanced Institute of Science and Technology, or KAIST, have developed an ultra-thin actuator for soft robotics. The artificial muscles, recently reported in the journal Science Robotics, were demonstrated with a robotic blooming flower brooch, dancing robotic butterflies, and fluttering tree leaves on a kinetic art piece. Actuators are the robotic equivalents of muscles, expanding, contracting, or rotating like muscle fibers in response to a stimulus such as electricity. Engineers around the world are striving to develop more dynamic actuators that respond quickly, can bend without breaking, and are very durable. Soft robotic muscles could have a wide variety of applications, from wearable electronics to advanced prosthetics.

From their first years of life, human beings have the innate ability to learn continuously and build mental models of the world, simply by observing and interacting with things or people in their surroundings. Cognitive psychology studies suggest that humans make extensive use of this previously acquired knowledge, particularly when they encounter new situations or when making decisions. Despite the significant recent advances in the field of artificial intelligence (AI), most virtual agents still require hundreds of hours of training to achieve human-level performance in several tasks, while humans can learn how to complete these tasks in a few hours or less. Recent studies have highlighted two key contributors to humans' ability to acquire knowledge so quickly--namely, intuitive physics and intuitive psychology. These intuition models, which have been observed in humans from early stages of development, might be the core facilitators of future learning.