Kim+Jaechul+Graduate+School+of+AI
-
KAIST Introduces ‘Virtual Teaching Assistant’ That can Answer Even in the Middle of the Night – Successful First Deployment in Classroom
- Research teams led by Prof. Yoonjae Choi (Kim Jaechul Graduate School of AI) and Prof. Hwajeong Hong (Department of Industrial Design) at KAIST developed a Virtual Teaching Assistant (VTA) to support learning and class operations for a course with 477 students.
- The VTA responds 24/7 to students’ questions related to theory and practice by referencing lecture slides, coding assignments, and lecture videos.
- The system’s source code has been released to support future development of personalized learning support systems and their application in educational settings.
< Photo 1. (From left) PhD candidate Sunjun Kweon, Master's candidate Sooyohn Nam, PhD candidate Hyunseung Lim, Professor Hwajung Hong, Professor Yoonjae Choi >
“At first, I didn’t have high expectations for the Virtual Teaching Assistant (VTA), but it turned out to be extremely helpful—especially when I had sudden questions late at night, I could get immediate answers,” said Jiwon Yang, a Ph.D. student at KAIST. “I was also able to ask questions I would’ve hesitated to bring up with a human TA, which led me to ask even more and ultimately improved my understanding of the course.”
KAIST (President Kwang Hyung Lee) announced on June 5th that a joint research team led by Prof. Yoonjae Choi of the Kim Jaechul Graduate School of AI and Prof. Hwajeong Hong of the Department of Industrial Design has successfully developed and deployed a Virtual Teaching Assistant (VTA) that provides personalized feedback to individual students even in large-scale classes.
This study marks one of the first large-scale, real-world deployments in Korea, where the VTA was introduced in the “Programming for Artificial Intelligence” course at the KAIST Kim Jaechul Graduate School of AI, taken by 477 master’s and Ph.D. students during the Fall 2024 semester, to evaluate its effectiveness and practical applicability in an actual educational setting.
The AI teaching assistant developed in this study is a course-specialized agent, distinct from general-purpose tools like ChatGPT or conventional chatbots. The research team implemented a Retrieval-Augmented Generation (RAG) architecture, which automatically vectorizes a large volume of course materials—including lecture slides, coding assignments, and video lectures—and uses them as the basis for answering students’ questions.
< Photo 2. Teaching Assistant demonstrating to the student how the Virtual Teaching Assistant works>
When a student asks a question, the system searches for the most relevant course materials in real time based on the context of the query, and then generates a response. This process is not merely a simple call to a large language model (LLM), but rather a material-grounded question answering system tailored to the course content—ensuring both high reliability and accuracy in learning support.
Sunjun Kweon, the first author of the study and head teaching assistant for the course, explained, “Previously, TAs were overwhelmed with repetitive and basic questions—such as concepts already covered in class or simple definitions—which made it difficult to focus on more meaningful inquiries.” He added, “After introducing the VTA, students began to reduce repeated questions and focus on more essential ones. As a result, the burden on TAs was significantly reduced, allowing us to concentrate on providing more advanced learning support.”
In fact, compared to the previous year’s course, the number of questions that required direct responses from human TAs decreased by approximately 40%.
< Photo 3. A student working with VTA. >
The VTA, which was operated over a 14-week period, was actively used by more than half of the enrolled students, with a total of 3,869 Q&A interactions recorded. Notably, students without a background in AI or with limited prior knowledge tended to use the VTA more frequently, indicating that the system provided practical support as a learning aid, especially for those who needed it most.
The analysis also showed that students tended to ask the VTA more frequently about theoretical concepts than they did with human TAs. This suggests that the AI teaching assistant created an environment where students felt free to ask questions without fear of judgment or discomfort, thereby encouraging more active engagement in the learning process.
According to surveys conducted before, during, and after the course, students reported increased trust, response relevance, and comfort with the VTA over time. In particular, students who had previously hesitated to ask human TAs questions showed higher levels of satisfaction when interacting with the AI teaching assistant.
< Figure 1. Internal structure of the AI Teaching Assistant (VTA) applied in this course. It follows a Retrieval-Augmented Generation (RAG) structure that builds a vector database from course materials (PDFs, recorded lectures, coding practice materials, etc.), searches for relevant documents based on student questions and conversation history, and then generates responses based on them. >
Professor Yoonjae Choi, the lead instructor of the course and principal investigator of the study, stated, “The significance of this research lies in demonstrating that AI technology can provide practical support to both students and instructors. We hope to see this technology expanded to a wider range of courses in the future.”
The research team has released the system’s source code on GitHub, enabling other educational institutions and researchers to develop their own customized learning support systems and apply them in real-world classroom settings.
< Figure 2. Initial screen of the AI Teaching Assistant (VTA) introduced in the "Programming for AI" course. It asks for student ID input along with simple guidelines, a mechanism to ensure that only registered students can use it, blocking indiscriminate external access and ensuring limited use based on students. >
The related paper, titled “A Large-Scale Real-World Evaluation of an LLM-Based Virtual Teaching Assistant,” was accepted on May 9, 2025, to the Industry Track of ACL 2025, one of the most prestigious international conferences in the field of Natural Language Processing (NLP), recognizing the excellence of the research.
< Figure 3. Example conversation with the AI Teaching Assistant (VTA). When a student inputs a class-related question, the system internally searches for relevant class materials and then generates an answer based on them. In this way, VTA provides learning support by reflecting class content in context. >
This research was conducted with the support of the KAIST Center for Teaching and Learning Innovation, the National Research Foundation of Korea, and the National IT Industry Promotion Agency.
2025.06.05 View 549 -
KAIST Proposes a New Way to Circumvent a Long-time Frustration in Neural Computing
The human brain begins learning through spontaneous random activities even before it receives sensory information from the external world. The technology developed by the KAIST research team enables much faster and more accurate learning when exposed to actual data by pre-learning random information in a brain-mimicking artificial neural network, and is expected to be a breakthrough in the development of brain-based artificial intelligence and neuromorphic computing technology in the future.
KAIST (President Kwang-Hyung Lee) announced on the 16th of December that Professor Se-Bum Paik 's research team in the Department of Brain Cognitive Sciences solved the weight transport problem*, a long-standing challenge in neural network learning, and through this, explained the principles that enable resource-efficient learning in biological brain neural networks.
*Weight transport problem: This is the biggest obstacle to the development of artificial intelligence that mimics the biological brain. It is the fundamental reason why large-scale memory and computational work are required in the learning of general artificial neural networks, unlike biological brains.
Over the past several decades, the development of artificial intelligence has been based on error backpropagation learning proposed by Geoffery Hinton, who won the Nobel Prize in Physics this year. However, error backpropagation learning was thought to be impossible in biological brains because it requires the unrealistic assumption that individual neurons must know all the connected information across multiple layers in order to calculate the error signal for learning.
< Figure 1. Illustration depicting the method of random noise training and its effects >
This difficult problem, called the weight transport problem, was raised by Francis Crick, who won the Nobel Prize in Physiology or Medicine for the discovery of the structure of DNA, after the error backpropagation learning was proposed by Hinton in 1986. Since then, it has been considered the reason why the operating principles of natural neural networks and artificial neural networks will forever be fundamentally different.
At the borderline of artificial intelligence and neuroscience, researchers including Hinton have continued to attempt to create biologically plausible models that can implement the learning principles of the brain by solving the weight transport problem.
In 2016, a joint research team from Oxford University and DeepMind in the UK first proposed the concept of error backpropagation learning being possible without weight transport, drawing attention from the academic world. However, biologically plausible error backpropagation learning without weight transport was inefficient, with slow learning speeds and low accuracy, making it difficult to apply in reality.
KAIST research team noted that the biological brain begins learning through internal spontaneous random neural activity even before experiencing external sensory experiences. To mimic this, the research team pre-trained a biologically plausible neural network without weight transport with meaningless random information (random noise).
As a result, they showed that the symmetry of the forward and backward neural cell connections of the neural network, which is an essential condition for error backpropagation learning, can be created. In other words, learning without weight transport is possible through random pre-training.
< Figure 2. Illustration depicting the meta-learning effect of random noise training >
The research team revealed that learning random information before learning actual data has the property of meta-learning, which is ‘learning how to learn.’ It was shown that neural networks that pre-learned random noise perform much faster and more accurate learning when exposed to actual data, and can achieve high learning efficiency without weight transport.
< Figure 3. Illustration depicting research on understanding the brain's operating principles through artificial neural networks >
Professor Se-Bum Paik said, “It breaks the conventional understanding of existing machine learning that only data learning is important, and provides a new perspective that focuses on the neuroscience principles of creating appropriate conditions before learning,” and added, “It is significant in that it solves important problems in artificial neural network learning through clues from developmental neuroscience, and at the same time provides insight into the brain’s learning principles through artificial neural network models.”
This study, in which Jeonghwan Cheon, a Master’s candidate of KAIST Department of Brain and Cognitive Sciences participated as the first author and Professor Sang Wan Lee of the same department as a co-author, was presented at the 38th Neural Information Processing Systems (NeurIPS), the world's top artificial intelligence conference, on December 14th in Vancouver, Canada. (Paper title: Pretraining with random noise for fast and robust learning without weight transport)
This study was conducted with the support of the National Research Foundation of Korea's Basic Research Program in Science and Engineering, the Information and Communications Technology Planning and Evaluation Institute's Talent Development Program, and the KAIST Singularity Professor Program.
2024.12.16 View 5940 -
Professor Joseph J. Lim of KAIST receives the Best System Paper Award from RSS 2023, First in Korea
- Professor Joseph J. Lim from the Kim Jaechul Graduate School of AI at KAIST and his team receive an award for the most outstanding paper in the implementation of robot systems.
- Professor Lim works on AI-based perception, reasoning, and sequential decision-making to develop systems capable of intelligent decision-making, including robot learning
< Photo 1. RSS2023 Best System Paper Award Presentation >
The team of Professor Joseph J. Lim from the Kim Jaechul Graduate School of AI at KAIST has been honored with the 'Best System Paper Award' at "Robotics: Science and Systems (RSS) 2023".
The RSS conference is globally recognized as a leading event for showcasing the latest discoveries and advancements in the field of robotics. It is a venue where the greatest minds in robotics engineering and robot learning come together to share their research breakthroughs. The RSS Best System Paper Award is a prestigious honor granted to a paper that excels in presenting real-world robot system implementation and experimental results.
< Photo 2. Professor Joseph J. Lim of Kim Jaechul Graduate School of AI at KAIST >
The team led by Professor Lim, including two Master's students and an alumnus (soon to be appointed at Yonsei University), received the prestigious RSS Best System Paper Award, making it the first-ever achievement for a Korean and for a domestic institution.
< Photo 3. Certificate of the Best System Paper Award presented at RSS 2023 >
This award is especially meaningful considering the broader challenges in the field. Although recent progress in artificial intelligence and deep learning algorithms has resulted in numerous breakthroughs in robotics, most of these achievements have been confined to relatively simple and short tasks, like walking or pick-and-place. Moreover, tasks are typically performed in simulated environments rather than dealing with more complex, long-horizon real-world tasks such as factory operations or household chores. These limitations primarily stem from the considerable challenge of acquiring data required to develop and validate learning-based AI techniques, particularly in real-world complex tasks.
In light of these challenges, this paper introduced a benchmark that employs 3D printing to simplify the reproduction of furniture assembly tasks in real-world environments. Furthermore, it proposed a standard benchmark for the development and comparison of algorithms for complex and long-horizon tasks, supported by teleoperation data. Ultimately, the paper suggests a new research direction of addressing complex and long-horizon tasks and encourages diverse advancements in research by facilitating reproducible experiments in real-world environments.
Professor Lim underscored the growing potential for integrating robots into daily life, driven by an aging population and an increase in single-person households. As robots become part of everyday life, testing their performance in real-world scenarios becomes increasingly crucial. He hoped this research would serve as a cornerstone for future studies in this field.
The Master's students, Minho Heo and Doohyun Lee, from the Kim Jaechul Graduate School of AI at KAIST, also shared their aspirations to become global researchers in the domain of robot learning. Meanwhile, the alumnus of Professor Lim's research lab, Dr. Youngwoon Lee, is set to be appointed to the Graduate School of AI at Yonsei University and will continue pursuing research in robot learning.
Paper title: Furniture Bench: Reproducible Real-World Benchmark for Long-Horizon Complex Manipulation. Robotics: Science and Systems.
< Image. Conceptual Summary of the 3D Printing Technology >
2023.07.31 View 9596