User-centered Knowledge Services that Support Advanced Intellectual Activities
Research Areas
Publications
Current Projects
"Every Error has Its Magnitude: Asymmetric Mistake Severity Training for Multiclass Multiple Instance Learning", Sungrae Hong, Jiwon Jeong, Jisu Shin, Donghee Han, Sol Lee, Kyungeun Kim & Mun Yi.
“Diagnose Like A REAL Pathologist: An Uncertainty-Focused Approach for Trustworthy Multi-Resolution Multiple Instance Learning”, Sungrae Hong, Sol Lee, Jisu Shin, Jiwon Jeong, & Mun Yi.
“Few-Shot Learning from Gigapixel Images via Hierarchical Vision-Language Alignment and Modeling”, Bryan Wong*, Jongwoo Kim*, Huazhu Fu, & Mun Yi.
“RAG-based Unanswerable Question Detection in Clinical Text-to-SQL”, Donghee Han, Seungjae Lim, & Mun Yi.
“Leveraging Multi-facet Paths for Heterogeneous Graph Representation Learning”, Jongwoo Kim, Seongyeub Chu, Hyeongmin Park, Bryan Wong, Keejun Han, & Mun Yi.
“A Novel Evaluation Framework for 15-Minute City Using Satellite Imagery”, Chan Jae Song*, Seong Yeub Chu*, Jong Woo Kim*, & Mun Yong Yi.
“Rethinking LLM-Based Recommendations: A Personalized Query-Driven Parallel Integration”, Donghee Han, Hwanjun Song, & Mun Y. Yi.
“Not All Options Are Created Equal: Textual Option Weighting for Token-Efficient LLM-Based Knowledge Tracing”, Jong Woo Kim*, SeongYeub Chu*, Bryan Wong, & Mun Y. Yi.
“Priority-Aware Clinical Pathology Hierarchy Training for Multiple Instance Learning”, Sungrae Hong, Kyungeun Kim, Juhyeon Kim, Sol Lee, Jisu Shin, Chanjae Song, & Mun Yi. (Best Paper Award)
“MicroMIL: Graph-Based Multiple Instance Learning for Context-Aware Diagnosis with Microscopic Images”, Jongwoo Kim*, Bryan Wong*, Huazhu Fu, Willmer Rafell Quinones, Young Sin Ko, & Mun Yong Yi.
“Rationale Behind Essay Scores: Enhancing S-LLM's Multi-Trait Essay Scoring with Rationale Generated by LLMs”, Seong Yeub Chu*, Jong Woo Kim*, Bryan Wong, & Mun Yong Yi.
“More Intra-Class Diversity in Few-Shot Text Classification with Many Classes”, G. Jang, H. J. Jeong, & M. Y. Yi, Knowledge-Based Systems. (SCIE, Impact factor: 7.6) [Link]
“Fine-Grained Multi-Prompt Essay Scoring with Multi-Level Disentanglement”, D. Han, D. Roh, E. Han, H. Song, & M. Y. Yi, Data Mining and Knowledge Discovery. (SCIE, Impact factor: 5.3) [Link]
"Leveraging Pretrained Knowledge at Inference Time: LoRA-Gated Contrastive Decoding for Multilingual Factual Language Generation in Adapted LLMs", Gwangseon Jang, Hongseok Choi, Chanuk Lim, Kyong-Ha Lee & Mun Y.
“Think Together and Work Better: Combining Humans' and LLMs' Think-Aloud Outcomes for Effective Text Evaluation”, Seong Yeub Chu*, Jong Woo Kim*, & Mun Yong Yi.
“Towards Classifying Histopathological Microscope Images as Time Series Data”, Sungrae Hong, Hyeongmin Park, Youngsin Ko, Sol Lee, Bryan Wong, & Mun Yong Yi.
“Rethinking Pre-Trained Feature Extractor Selection in Multiple Instance Learning for Whole Slide Image Classification”, Bryan Wong, Sungrae Hong, & Mun Yong Yi.
“TireDiff: A Diffusion-based Tire Footprint Image Generation Framework for High-fidelity Prototyping”, Sol Lee, Jisu Shin, Sungrae Hong, Chanjae Song, Youngbin You, Jeongheon Park, Jungsoo Oh, & Mun Yong Yi.
“Accelerating Manufacturing Prototyping: A Continual Learning Approach for Imbalanced Sequential Image Generation”, Jisu Shin, Sol Lee, Youngbin You, Jeongheon Park, Jungsoo Oh, & Mun Yong Yi.
“CTIP: Towards Accurate Tabular-to-Image Generation for Tire Footprint Generation”, Daeyoung Roh, Donghee Han, Jihyun Nam, Jungsoo Oh, Youngbin You, Jeongheon Park, & Mun Yong Yi.
“Uncertainty-based Data-wise Label Smoothing for Calibrating Multiple Instance Learning in Histopathology Image Classification”, Hyeongmin Park, Sungrae Hong, Chanjae Song, Jongwoo Kim, & Mun Yong Yi.
“Leveraging LLM-Generated Schema Descriptions for Unanswerable Question Detection in Clinical Data”, Donghee Han, Seungjae Lim, Daeyoung Roh, Sangryul Kim, Sehyun Kim, & Mun Yong Yi.
“Leveraging Commonality across Multiple Tissue Slices for Enhanced Whole Slide Image Classification Using Graph Convolutional Networks”, S. Noree, W. R. Quiñones Robles, Y. S. Ko, & M. Y. Yi, BMC Medical Imaging. (SCIE, Impact factor: 2.8) [Link]
Jongwoo Kim, SeongYeub Chu and SeungTai Yoo, received the Best Paper Award in the track of Applied AI at KCC 2024 which is the largest conference in the computer science field in Korea.
Roh Dae-young, a master's degree student in our lab, won the Excellence Award and 1 million won at the Winning Hankook TIRE-KAIST AI Competition with two Hankook Tire employees.
Hong Seong-Rae, a Ph.D. student in our lab, won the Genesis Lab Award and a prize of 1 million won at the 2023 Military AI Competition.
Roh Dae-young, a master's degree student in our lab, won the Excellence Award and 1 million won at the Winning Hankook TIRE-KAIST AI Competition with two Hankook Tire employees.
Kim, Yu Sung(Edward), a Ph.D. student in our lab, won the Global Leadership Award as an example of others in recognition of his outstanding spirit and process of challenge, creativity, and consideration, which are the core values of KAIST.
Kim, Yu Sung(Edward), a Ph.D. student in our lab, and P.S. Chung, a graduate of the medical school, won the grand prize at the 2022 Convergence Research Revitalization Idea Contest organized by the 2022 Korea Science and Technology Future Convergence Forum.
Willmer Rafell Quiñones Robles, Mujin Kim, PhD students in our lab and Sung Rae Hong, Tae Mi Kim, Sol Lee, Jongwoo Kim, Master's students in our lab won Industrial/Social Problem Solving Poster Contest of 2022 ISysE Research Day and 700 thousand won in prize.
At the 2022 ETRI Human Understanding AI Paper Competition (sponsored by the ETRI, the MSIT, and the NST), Master's students, SungRae Hong, TaeMi Kim, Sol Lee and JongWoo Kim won the MSIT Minister's Award and 2 million won in prize.
Kim, Yu Sung(Edward), a Ph.D.'s student in our lab has been awarded prestigious Kwanjeong Scholarship from Kwanjeong Lee, Chonghwan Educational Foundation. The selection was made out of nation-wide competition.
지식서비스는 미래를 이끄는 자원이 될 것
"빅데이터란 스마트 폰과 소셜 네트워크 서비스의 발전으로 엄청난 양의 데이터가 빠른 속도로 생산되는 것을 말한다. 비정형데이터인 빅데이터와 기존 정형데이터간의 융합이 앞으로 더 중요해질것. "
지금은 빅 데이터 관련기술 개발 절정의 시기
"빅 데이터의 규모, 다양성, 속도 등은 새로운 통찰력(insight)을 제공한다. 빅 데이터를 분석하면 고객이 무엇을 원하는지, 시장은 어떤 방향으로 변하는지, 업무환경은 어떻게 개선하는 게 바람직한지 등에 대한 답을 얻을 수 있다. 빅 데이터가 빅 인사이트(Big Insight)를 가져오고, 빅 인사이트(Big Insight)가 빅 밸류(Big Value)를 낳는셈."
카이스트 교수가 대학생 벤쳐에 투자한 투자한 이유
"카이스트 학생처럼 '가진자'들이 스스로 '빚진자'로 여기며 자신이 가진 지식을 기부한다는 점은 보람있고 기특한 일이기에 투자를 결정."
Phone: +82 42 350 3105
Fax: +82 42 350 3110
Location: Room 1201, Bldg. E2-1, KAIST 291 Daehak-ro, Yuseong-gu, Daejeon 305-701
E-mail:
munyi@kaist.ac.kr
