%50%68%79%73%69%63%61%6c%20%41%49
-
"Age of Robots Making Human-Like Judgments, KAIST Solves Key Challenge in Physical AI
< (From left) Professor Chang D. Yoo, Tung M. Luu (PhD candidate, first author) at the back center, and Hwanhee Kim (M.S candidate, second author) at the front right >
“Robots that make judgments like humans are coming faster than we think.” A core technology that will accelerate the era where robots understand human intentions and choose the correct actions on their own has been developed in South Korea. KAIST researchers solved a key challenge in the commercialization of physical AI by developing a technology where AI learns human judgment criteria on its own with just a few videos. KAIST announced on June 10th that a research team led by Professor Chang D. Yoo from the School of Electrical Engineering has developed 'VOTP (Video-based Optimal TransPort Preference)' for the first time in the world, a new technology that allows AI to learn human intentions and judgment criteria using just a few preference videos instead of thousands to tens of thousands of human evaluation data points.
< VOTP Overview Diagram >
The research team's paper has been accepted to ICML (International Conference on Machine Learning) 2026, the world's most prestigious AI conference, which will be held at COEX in Seoul this July. It was selected for an Oral presentation, an honor given to only the top 0.7% (168 papers) out of all submitted papers (23,918 papers), recognizing the excellence of the research. ICML is considered one of the most influential international conferences in the fields of AI and machine learning. Recently, AI technology is rapidly evolving beyond generative AI that writes text and draws pictures into the era of 'Physical AI,' which moves actual machines and acts in the real world. Representative examples include robots that perform dangerous tasks in factories instead of humans, autonomous vehicles that judge road situations on their own, and medical robots that perform delicate surgeries. However, there was a barrier that had to be overcome for the practical application of physical AI. It is the problem of learning human-level evaluation criteria to judge whether the actions performed by a machine match human intentions and which actions are more desirable. For example, when a surgical robot performs suturing or an autonomous vehicle passes through a complex intersection, the AI must choose the most appropriate action among numerous options. To achieve this, a 'Reward Function' that reflects human preferences and judgment criteria is required. However, until now, humans had to directly evaluate thousands to tens of thousands of action data points to build this, which required an enormous amount of time and cost. The research team focused on the way humans learn new tasks after seeing just a few demonstrations. VOTP, developed by the research team, helps AI understand human-preferred action patterns on its own with just a few videos of good and bad examples. Even without humans evaluating a vast amount of data one by one as before, AI can understand human judgment criteria and expand its learning to various situations. The core idea of this research is that intelligent machines such as robots or autonomous vehicles can quickly grasp human intents with only a small number of videos containing human preferences. The algorithm developed for this purpose proved its effectiveness and generalization performance through extensive experiments across various environments and tasks. This method can significantly reduce human feedback and data construction costs required for physical AI development. Since robots, autonomous vehicles, and industrial machinery can learn actions that meet human expectations with only a small number of examples, it is expected to drastically shorten development time and costs. The technology can be widely applied not only to robot arm control, humanoid robots, autonomous vehicles, smart factories, drones, and surgical robots, but also to AI agents that directly operate computers. In particular, it is expected to be utilized as a core foundational technology for all physical AI systems that need to learn human intention and satisfaction.
< VOTP Research Image (AI Generated) >
Professor Chang D. Yoo said, "The core of physical AI is making machines understand human intentions and choose the correct actions," and added, "Since VOTP can learn human judgment criteria with only a small number of videos, it is a core technology that will accelerate the era of robots making human-like judgments." This research, in which PhD student Tung M. Luu from the School of Electrical Engineering participated as the first author, was selected as an Oral presentation paper at ICML (International Conference on Machine Learning) 2026, the world's most prestigious AI conference. ※ Paper Title: Video-Based Optimal Transport for Feedback-Efficient Offline Preference-Based Reinforcement Learning, Paper File: https://sanctusfactory.com/data/file/publications/202606091714078906.pdf This research was conducted with support from the Institute for Information & Communication Technology Planning & Evaluation (IITP) and the National Research Foundation of Korea (NRF), funded by the Ministry of Science and ICT."
2026.06.10 View 1608 -
KAIST Develops AI Technology That Automatically Generates Sounds as If a “Jurassic Park” Dinosaur Were Actually Walking Toward You
<(From Left) Hyun-Bin Oh, Takida Yuhta, Uesaka Toshimitsu, Tae-Hyun Oh, Mitsufuji Yuki>
When people watch a scene in the film Jurassic Park where a giant dinosaur walks toward them, they naturally imagine a heavy, rumbling sound, as if the ground were shaking. This is because humans predict sound by considering not only the shape of an object, but also physical properties such as its size, weight, and speed of movement. However, existing video-to-audio generation AI mainly generates sound based on the category of objects or scene information in the video, and has not sufficiently reflected physical properties that vary depending on weight or speed.
KAIST (President Kwang Hyung Lee) announced on the 26th of May that a collaborative research team involving Professor Tae-Hyun Oh of the School of Computing, KAIST, together with joint researchers from POSTECH (President Sung Keun Kim) and Sony AI, has developed “PAVAS (Physics-Aware Video-to-Audio Synthesis),” an artificial intelligence (AI) technology that understands the physical situation in a video and generates more realistic sound.
<Concept Diagram of PAVAS (Physics-Aware Video-to-Audio Synthesis) Technology>
The key feature of this technology is that it is designed so that AI can infer invisible physical information such as the mass and velocity of objects in a video on its own. Ordinary videos do not provide exact numerical values for an object’s weight or speed, but the research team enabled AI to estimate them by analyzing the surrounding environment and movement context, and to reflect the results in the sound generation process.
In other words, the AI was designed to go beyond simply recognizing “what is visible” and to understand the physical cause of “why this sound should occur.”
As a result of technical validation, the research team’s AI generated sounds very similar to real-world environments in scenes involving physical interactions such as collisions or impacts between objects. In particular, it produced more realistic audio in which loudness and tone naturally changed when the mass and velocity of objects varied.
Recently, generative AI technologies that simultaneously generate video and audio have been advancing rapidly. Representative examples include Google’s “Veo 3” and ByteDance’s “Seedance 2.0.” However, in actual film, advertising, and game production sites, there is far greater demand for post-production work that adds sound effects suited to existing video scenes or supplements audio than for generating entirely new videos.
While existing commercial AI models have focused on generating video and audio together, PAVAS is differentiated by its ability to analyze the movement and collision characteristics of objects in a video and generate realistic sound effects that precisely match the scene.
<Comparison of Spectrograms Generated by Conventional Video-to-Audio Models and PAVAS>
The research team explained that this technology presents new possibilities in the field of “Physical AI,” or physically consistent generative AI. Physically consistent generative AI refers to AI that goes beyond simply producing plausible results and understands the laws of physics and causal relationships in the real world.
In the future, this technology is expected to provide more immersive user experiences in a wide range of fields, including the automation of content sound production, augmented reality (AR) and virtual reality (VR) content, the metaverse, and robotics simulation.
Professor Tae-Hyun Oh stated, “While existing generative AI has developed by increasing the scale of data and models, this research is meaningful in that it was designed so that AI directly understands physical quantities and causal relationships,” adding, “In the future, it can be expanded into a core foundational technology for next-generation multimodal AI that simultaneously understands and processes diverse types of information, including text, video, and speech.”
This study was led by POSTECH integrated M.S.-Ph.D. student Hyun-Bin Oh as the first author, with KAIST Professor Tae-Hyun Oh and Sony AI researchers Yuhta Takida, Toshimitsu Uesaka, and Yuki Mitsufuji participating as co-authors. This research was selected as an Oral presentation paper at CVPR 2026 (Computer Vision and Pattern Recognition 2026), the world’s most prestigious academic conference in the field of computer vision (image-based artificial intelligence technology), where only the top 0.88% of all papers are selected for oral presentation, recognizing the excellence of the work. The presentation is scheduled to take place on June 6.
※ Paper title: “PAVAS: Physics-Aware Video-to-Audio Synthesis,” DOI: https://arxiv.org/abs/2512.08282
This research was supported by the Mid-Career Research Program under the Basic Research Program of the Ministry of Science and ICT, the Pioneer Research Program for Future Converging Technology of the Ministry of Science, ICT and Future Planning, the AGI Program of the Ministry of Science and ICT, and the KAIST InnoCORE Program.
2026.05.27 View 1127 -
World’s First AI-Managed Unmanned Factory Implemented... Construction of Physical AI KAIROS
< Integrated Operation of Heterogeneous Logistics Robot Systems >
KAIST announced on March 23rd that Professor Young Jae Jang's team from the Department of Industrial and Systems Engineering has constructed ‘KAIROS’ (KAIST AI Robot Orchestration Systems), a physical AI testbed that integrates and controls heterogeneous robots, sensors, facilities, and digital twins into a single system.
KAIROS is a 100% unmanned factory platform based on physical AI and is the first integrated testbed of its kind in Korea, developed with support from the Ministry of Science and ICT (MSIT). It is particularly noteworthy as a domestic integrated solution aimed at exporting "Dark Factories" in the future.
The most significant feature of KAIROS is its structure, which integrates and controls various factory equipment through a single AI agent-based Operating System (OS). While existing factory automation was operated around individual devices, KAIROS integrates Autonomous Mobile Robots (AMR), humanoid robots, collaborative robots, and automation facilities into a single intelligent platform. Through this, the concept of ‘Physical AI-based factory operation’—where the entire factory is operated like a single AI system—has been realized.
The core of this testbed is the 100% domestic integration of the entire process from sensors and control to data processing. By integrating key elements of a Dark Factory—including logistics robots (AMR), OHT, 3D shuttles, humanoid robots, collaborative robots, industrial sensors and PC controllers, wireless charging systems, digital twins and simulations, and AI-based integrated control and safety management systems—using domestic technology, the project has replaced factory automation equipment and software that were heavily dependent on foreign technology and laid the foundation for a ‘K-Manufacturing Factory Export Model.’
As part of the Physical AI Pre-verification Project, the MSIT has supported the establishment of a demonstration lab within the KAIST Industrial Management Building. On March 23, Vice Minister Bae Gyeong-hoon (Minister of Science and ICT) visited KAIST to announce the National Physical AI Strategy (Draft) and unveil the KAIROS-based Dark Factory demonstration site.
At the event, the factory operating system of the KAIST demonstration lab, joint physical AI demonstration results with Chonbuk National University, and the direction of the ‘Team Korea Physical AI (TK-PAI)’ alliance—a cooperative structure of domestic companies—were discussed.
< KAIROS Operation Plan Announcement >
< KAIROS Demonstration >
< KAIROS Factory Site >
KAIST plans to further advance the next-generation factory operating system (OS), covering the design, construction, and operation of Dark Factories through KAIROS, and to develop simulation and virtual verification environments.
In addition, the university intends to utilize the platform as a testing and evaluation site where domestic robot and automation companies can pre-verify highly reliable equipment, thereby increasing industrial applicability. Furthermore, the goal is to develop physical AI-based Dark Factory solutions capable of competing with global companies such as Siemens (Germany), FANUC (Japan), and Yaskawa (Japan) to pursue entry into the global market.
Kwang Hyung Lee, President of KAIST, stated, “KAIROS is the beginning of a new industrial paradigm where AI directly operates factories. KAIST will lead manufacturing innovation based on physical AI and contribute to ensuring South Korea’s leadership in global industrial competition.”
Professor Young Jae Jang, who led the construction of KAIROS, explained, “KAIROS goes beyond individual automation technologies to implement the concept of a factory operating system (OS) that integrates diverse robots and facilities into one system. It will serve as a foundation for domestic companies to verify physical AI technologies applicable to actual industrial sites and expand into the global market.”
2026.03.23 View 4329 -
KAIST Launches Deep-Tech Scale-up Valley, Unveils Execution Strategies for Physical AI
< Progress Report Meeting of the Deep-Tech Scale-up Valley Project >
KAIST announced on February 27th that it held the "Deep-Tech Scale-up Valley Project Progress Report Meeting" at its main campus in Daejeon on the 26th. During the meeting, the university unveiled its Physical AI strategies and execution structures, currently being developed with a focus on robotics.
The Deep-Tech Scale-up Valley Promotion Project is a joint initiative by the Ministry of Science and ICT, Daejeon Metropolitan City, and KAIST. KAIST has secured a total budget of 13.65 billion KRW for a period of three years and six months, starting from 2025. The project aims to commercialize KAIST's deep-tech capabilities in robotics to build a robust robot innovation ecosystem. A "Robot Alliance" has been formed, led by KAIST (headed by Professor Jung Kim) and including KAIST Holdings, Daejeon Techno Park, Daejeon Center for Creative Economy & Innovation, Angel Robotics, and Eurobotics.
The project seeks to foster a virtuous cycle ecosystem and nurture future "Unicorn" companies based on a three-pillar framework: Technology Commercialization, Deep-Tech R&D, and Commercialization Scale-up. In its first year (2025), the project achieved 230 billion KRW in technology transfers and investment attraction through Physical AI lectures, startup pitching sessions, and investment networking.
Physical AI refers to technology that combines robotics with artificial intelligence, allowing machines to make autonomous decisions and act in the real world. While it is gaining traction as a core field of next-generation industry—with increasing government R&D, corporate investment, and startup activity—critics have noted that successful business models applicable to actual industrial sites remain limited.
This report meeting is significant in that it redefined Physical AI not merely as a competition of AI technology, but as a matter of "industrial structure." It emphasized that commercialization is difficult unless R&D, industrial sites, and the investment ecosystem are organically linked.
Specifically, the report stated that for Physical AI to be applied to industrial sites, "meaningful data" generated from real-world operations is required, going beyond virtual environments. The strategy involves collaborating with skilled experts in manufacturing processes to accumulate data reflecting physical sensations and judgment, and establishing an execution system where robots can continuously cooperate with humans without obstructing their tasks.
Professor Kyoungchul Kong of the KAIST Department of Mechanical Engineering stated, "It is now crucial to clarify the mixed concepts of Physical AI and create a concrete platform that anyone can utilize." He added, "For AI learned in virtual environments to function properly with actual robots in the real world, we must not only improve the accuracy of virtual technologies but also ensure that physical variables in the real world are predictable and stably managed." In simpler terms, technology is needed to ensure that a robot's performance in a simulation translates seamlessly to the real world.
Professor Hyun Myung of the KAIST School of Electrical Engineering highlighted, "In the field of AI, research on Physics-Informed Neural Networks (PINN), which incorporate physical laws into the learning process, is actively underway." He emphasized, "The completion of Physical AI is possible only when hardware researchers, who understand actual physical systems, and AI researchers, who implement these into learning structures, are organically integrated. We need AI that understands physical principles, going beyond simply learning massive amounts of data."
Based on this execution structure, KAIST plans to establish a clear Value Chain connecting researchers, industrial experts, and corporations. The strategy is to expand Physical AI from lab-scale demonstrations to technologies that solve real-world industrial problems.
Jung Kim, Head of the KAIST Department of Mechanical Engineering, stated, "We have moved past the era of competing on data volume; now is the time to contemplate how to execute AI in the physical world. Based on KAIST's specific preparations and execution strategies, we will support startups and companies to succeed in the commercialization of Physical AI."
Meanwhile, the Deep-Tech Scale-up Valley Project plans to step-by-step promote the establishment of a Physical AI platform, startup discovery and investment expansion, the creation of verification testbeds, and the expansion of cooperation networks with global robotics companies.
2026.02.27 View 2943 -
KAIST Wins Bid for ‘Physical AI Core Technology Demonstration’ Pilot Project
KAIST (President Kwang Hyung Lee) announced on the 28th of August that, together with Jeonbuk State, Jeonbuk National University, and Sungkyunkwan University, it has jointly won the Ministry of Science and ICT’s pilot project for the “Physical AI Core Technology Proof of Concept (PoC)”, with KAIST serving as the overall research lead. The consortium also plans to participate in a full-scale demonstration project that is expected to reach a total scale of 1 trillion KRW in the future.
In this project, KAIST led the research planning under the theme of “Collaborative Intelligence Physical AI.” Based on this, Jeonbuk National University and Jeonbuk State will carry out joint research and establish a collaborative intelligence physical AI industrial ecosystem within the province. The pilot project will begin on September 1 this year and will run until the end of the year over the next five years. Through this effort, Jeonbuk State aims to be built into a global hub for physical AI.
KAIST will take charge of developing original research technologies, creating a research environment through the establishment of a testbed, and promoting industrial diffusion. Professor Young Jae Jang of the Department of Industrial and Systems Engineering at KAIST, who is the overall project director, has been leading research on collaborative intelligence physical AI since 2016. His “Collaborative Intelligence-Based Smart Manufacturing Innovation Technology” was selected as one of KAIST’s “Top 10 Research Achievements” in 2019.
“Physical AI” refers to cutting-edge artificial intelligence technology that enables physical devices such as robots, autonomous vehicles, and factory automation equipment to perform tasks without human instruction by understanding spatiotemporal concepts.
In particular, collaborative intelligence physical AI is a technology in which numerous robots and automated devices in a factory environment work together to achieve goals. It is attracting attention as a key foundation for realizing “dark factories” in industries such as semiconductors, secondary batteries, and automobile manufacturing.
Unlike existing manufacturing AI, this technology does not necessarily require massive amounts of historical data. Through real-time, simulation-based learning, it can quickly adapt even to manufacturing environments with frequent changes and has been deemed a next-generation technology that overcomes the limitations of data dependency.
Currently, the global AI industry is led by LLMs that simulate linguistic intelligence. However, physical AI must go beyond linguistic intelligence to include spatial intelligence and virtual environment learning, requiring the organic integration of hardware such as robots, sensors, and motors with software. As a manufacturing powerhouse, Korea is well-positioned to build such an ecosystem and seize the opportunity to lead global competition.
In fact, in April 2025, KAIST won first place at INFORMS (Institute for Operations Research and the Management Sciences), the world’s largest industrial engineering society, with its case study on collaborative intelligence physical AI, beating MIT and Amazon. This achievement is recognized as proof of Korea’s global competitiveness in the physical AI technology realm.
Professor Young Jae Jang, KAIST’s overall project director, said, “Winning this large-scale national project is the result of KAIST’s collaborative intelligence physical AI research capabilities accumulated over the past decade being recognized both domestically and internationally. This will be a turning point for establishing Korea’s manufacturing industry as a global leading ‘Physical AI Manufacturing Innovation Model.’”
KAIST President Kwang Hyung Lee emphasized that “KAIST is taking on the role of leading not only academic research but also the practical industrialization of national strategic technologies. Building on this achievement, we will collaborate with Jeonbuk National University and Jeonbuk State to develop Korea into a world-class hub for physical AI innovation.”
Through this project, KAIST, Jeonbuk National University, and Jeonbuk State plan to develop Korea into a global industrial hub for physical AI.
2025.08.29 View 5130 -
KAIST Successfully Presents the Future of AI Transformation and Physical AI Strategy at the 1st National Strategic Technology Forum
<(Front row, fourth from the right) President Kwang Hyung Lee of KAIST, (back row, fifth from the right) Forum co-host Representative Hyung-Doo Choi, (back row, sixth from the left) Forum co-host Representative Han-Kyu Kim, along with ruling and opposition party members of the Science, ICT, Broadcasting, and Communications Committee and the Trade, Industry, Energy, SMEs, and Startups Committee, as well as Professors Hoe-Jun Yoo and Jung Kim from KAIST)>
KAIST (President Kwang Hyung Lee) announced on July that it had successfully held the “1st National Strategic Technology Forum” at the National Assembly Members' Office Building that day under the theme “The Future of Artificial Intelligence Transformation (AX): Physical AI.” This bipartisan policy forum aimed to discuss strategies for technology hegemony by leveraging Korea’s strengths in AI semiconductors and manufacturing.
The forum was hosted by KAIST and co-organized by Representative Hyung-Du Choi (People Power Party), the secretary of the National Assembly's Science, ICT, Broadcasting, and Communications Committee, and Representative Han-Kyu Kim (Democratic Party), a member of the Trade, Industry, Energy, SMEs, and Startups Committee. It marks the beginning of a five-part forum series, scheduled monthly through the rest of the year except for October.
The overarching theme, “Artificial Intelligence Transformation (AX),” was designed to address the structural changes reshaping industry, the economy, and society due to the spread of generative AI.
< KAIST President Kwang Hyung Lee delivering his remarks >
The first session focused on “Physical AI,” reflecting how AI innovation—sparked by the proliferation of large language models (LLMs)—is rapidly expanding into the physical realm through ultra-low-power, ultra-lightweight semiconductors. This includes applications in robotics, sensors, and edge devices. Physical AI refers to technologies that interact directly with the real world through AI integration with robotics, autonomous driving, and smart factories. It is drawing attention as a promising next-generation field where Korea can secure a strategic edge, given its strengths in semiconductors and manufacturing.
<Hoi-Jun Yoo, Dean of the KAIST Graduate School of AI Semiconductor>
Hoi-Jun Yoo, Dean of the KAIST Graduate School of AI Semiconductor, gave a presentation titled “The Second AI Innovation Enabled by Ultra-Low-Power AI Semiconductors and Lightweight AI Models,” covering semiconductor trends for implementing Physical AI, academic and industrial strategies for robotics and semiconductors, and Korea’s development direction for “K-Physical AI.”
<Professor Jung Kim, the head of KAIST’s Department of Mechanical and Aerospace Engineering>
Following that, Professor Jung Kim, the head of KAIST’s Department of Mechanical and Aerospace Engineering gave a talk on “Trends in Physical AI and Humanoid Robots,” predicting a new industrial paradigm shaped by AI-robot convergence. He presented global trends, Korea’s development trajectory, and survival strategies for humanoid robots that can supplement or replace human intellectual and physical functions.
During the open discussion that followed, participating lawmakers and experts engaged in in-depth conversations about the need for bipartisan strategies and collaboration.
Representative Hyung-Du Choi (People Power Party) stated, “Through this forum as a platform for public discourse, I will work to ensure that legislation and policy align with the direction of the science and technology field, and that necessary measures are taken promptly to strengthen national competitiveness.”
Representative Han-Kyu Kim (Democratic Party) emphasized, “As strategic planning in science and technology accelerates, it becomes more difficult to coordinate policies involving multiple ministries. Forums like this, which enable ongoing communication among stakeholders, are instrumental in finding effective solutions.”
KAIST President Kwang Hyung Lee remarked, “Although Korea is a latecomer in the generative AI field, we have a unique opportunity to gain strategic superiority in Physical AI, thanks to our technological capabilities in manufacturing, semiconductors, and robotics.” He added, “I hope lawmakers from both the ruling and opposition parties, along with experts, will come together regularly to devise practical policies and contribute to the advancement of Korea’s science and technology.”
<Poster of National Strategic Technology Forum>
This forum series aims to explore policy and institutional solutions to help Korea gain technological leadership in a global context where strategic technologies—such as AI, semiconductors, biotechnology, and energy—directly influence national security and economic sovereignty. Lawmakers from both the Science, ICT, Broadcasting, and Communications Committee and the Trade, Industry, Energy, SMEs, and Startups Committee will continue to participate, fostering bipartisan dialogue. The forums are coordinated by the KAIST Policy Research Institute for National Strategic Technologies.
2025.07.31 View 4663