A. 대표 논문
- From Scratch to Sketch: Deep Decoupled Hierarchical Reinforcement Learning for Robotic Sketching Agent, G.-H. Lee, M.-J. Kim, M. Lee, B.-T. Zhang, In Proceedings of the 2022 IEEE International Conference on Robotics and Automation (ICRA 2022), May 2022
- Goal-Aware Cross-Entropy for Multi-Target Reinforcement Learning, K. Kim, M. W. Lee, Y. Kim, J.-H. Ryu, M. Lee, B.-T. Zhang, Advances in Neural Information Processing Systems 34 (NeurIPS 2021), December 2021.
- Toward a Human-Level Video Understanding Intelligence, Y. -J. Heo, M. Lee, S. Choi, W. -S. Choi, M. Shin, M. Jung, J. -K. Ryu, B.-T. Zhang, Proceedings of the 2021 AAAI 2021 Fall Symposium (AAAI FSS 2021), 2021
- Toddler-Guidance Learning: Impacts of Critical Period on Multimodal AI Agents, J. -S. Park, K. -Y. Park, H. -S. Oh, G. -H. LEE, M. LEE, Y. -K. Lee, B. -T. Zhang, 23rd ACM International Conference on Multimodal Interaction (ICMI2021), October 2021.
- DramaQA: Character-Centered Video Story Understanding with Hierarchical QA, S.-H. Choi, K.-W. On, Y.-J Heo, A.-J. Seo, Y.-W. Jang, M. Lee and B.-T. Zhang, Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI 2021), February 2021.

B. 대표 연구과제
- 스스로 불확실성을 자각하며 질문하면서 성장하는 에이전트 기술 개발, 과학기술정보통신부/사람중심인공지능핵심원천기술개발사업, 2022.04.01~2026.12.31
- 새로운 문제를 해결하는 자기주도 인공지능 기술 개발, 과학기술정보통신부/사람중심인공지능핵심원천기술개발사업, 2022.04.01~2026.12.31
- 실세계 응용을 위한 목표 지향적인 자기주도 강화학습 기술 연구, 과학기술정보통신부/중견연구자지원사업, 2021.3.01~2024.2.29
- 인간을 물리적 상호작용을 통해 지원하는 로봇을 위한 가상현실 환경 인간시연을 모방하는 학습 기술 개발, 산업통상자원부/국제공동기술개발사업 2018.12.01~2022.03.31
- 비디오 튜링 테스트(Video Turing Test): 인간 수준의 비디오 이해 지능 및 검증 기술 개발, 과학기술정보통신부/혁신성장동력프로젝트, 2017.7.01~2021.12.31

○ 과제
- 창의도전연구기반지원과제 (2021.06-2023.05)
연구책임자
· 자폐 진단용 바이오마커 개발을 위한 멀티 오믹스 분석 시스템 개발
http://cb.snu.ac.kr
- 혁신성장 선도 고급연구인재 성장지원 과제 (KIURI) (2020.09-2021.08)
참여연구원
· 단백질 서열 임베딩을 이용한 Covid-19 감염 환자에서의 BCR 레퍼토리 분석
https://www.biorxiv.org/content/10.1101/2021.08.02.454701v3
○ 논문
- Kim I, Lee S, Kim Y, Namkoong H, Kim S*. ""A probabilistic model for pathway-guided gene set selection"" 2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 2021 Dec 10, [link]
- Kim I, Choi S, Kim S*. ""BRCA-Pathway: a structural integration and visualization system of TCGA breast cancer data on KEGG pathways"". BMC bioinformatics 19.1 (2018): 63-72. [link]
- Ahn H, Jung I, Chae H, Oh M, Kim I, Kim S*. ""IDEA: Integrating Divisive and Ensemble-Agglomerate hierarchical clustering framework for arbitrary shape data"" 2021 IEEE International Conference on Big Data (Big Data), 2021 Dec 15, [link]
- Lee AC, Lee Y, Choi A, Lee H, Shin K, Lee H, Kim J, Ryu H, Kim H, Ryu S, Lee S, Cheun J, Yoo D, Lee S, Choi H, Ryu T, Yeom H, Kim N, Noh J, Lee Y, Kim I, Bae S, Kim J, Lee W, Kim O, Jung Y, Kim C, Song S, Choi Y, Chung J, Kim B, Han W, Kwon S*. ""Spatial epitranscriptomics reveals A-to-I editome specific to cancer stem cell microniches"" Nature Communications 13.1 (2022): 1-12. [link]
○ 특허출원
- B 세포 수용체 단백질 서열을 이용한 면역 상태 진단 (출원번호10-2021-0100690)"

HetPipe: Enabling Large DNN Training on (Whimpy) Heterogeneous GPU Clusters through Integration of Pipelined Model Parallelism and Data Parallelism, USENIX ACT 2020
대규모 DNN 모델의 분산 학습을 위한 GPU 메모리 관리 연구, 한국연구재단/학문후속세대지원사업, 2021.9 - 2023.8

Sam Son, Seung Yul Lee, Yunho Jin, Jonghyun Bae, Jinkyu Jeong, Tae Jun Ham, Jae W. Lee, and Hongil Yoon, “ASAP: Fast Mobile Application Switch via Adaptive Prepaging”, in Proceedings of USENIX Annual Technical Conference (ATC), 2021
Shine Kim, Yunho Jin, Gina Sohn, Jonghyun Bae, Tae Jun Ham, and Jae W. Lee, “Behemoth: A Flash-centric Training Accelerator for Extreme-scale DNNs”, in Proceedings of USENIX Conference on File and Storage Technologies (FAST), 2021
Jonghyun Bae, Jongsung Lee, Yunho Jin, Sam Son, Shine Kim, Hakbeom Jang, Tae Jun Ham, and Jae W. Lee, “FlashNeuron: SSD-Enabled Large-Batch Training of Very Deep Neural Networks”, in Proceedings of USENIX Conference on File and Storage Technologies (FAST), 2021
Young H. Oh, Seonghak Kim, Yunho Jin, Sam Son, Jonghyun Bae, Jongsung Lee, Yeonhong Park, Dong Uk Kim, Tae Jun Ham, and Jae W. Lee, “Layerweaver: Maximizing Resource Utilization of Neural Processing Units via Layer-Wise Scheduling”, in Proceedings of IEEE International Symposium on High Performance Computer Architecture (HPCA), 2021
Jonghyun Bae, Hakbeom Jang, Jeonghun Gong, Wenjing Jin, Shine Kim, Jaeyoung Jang, Tae Jun Ham, Jinkyu Jeong, and Jae W. Lee, “SSDStreamer: Specializing I/O Stack for Large-Scale Machine Learning”, IEEE Micro, Sept/Oct 2019
Jonghyun Bae, Hakbeom Jang, Wenjing Jin, Jun Heo, Jaeyoung Jang, Joo-Young Hwang, Sangyeun Cho, and Jae W. Lee, “Jointly Optimizing Task Granularity and Concurrency for In-Memory MapReduce Frameworks”, in Proceedings of IEEE International Conference on Big Data (BigData), 2017
NAND 플래시 기반 심층신경망 학습 시스템, 과학기술정보통신부/이공분야기초연구사업, 2020.03.01--2023.02.28

논문
Bae, Y. S., et al. "Preliminary Evaluation of Calibrating Haptic Augmented Virtuality Systems."  18th International Conference on Control, Automation and Systems (ICCAS 2018). PyeongChang, GangWon, Korea . 2018.
Bae, Yoosung, Baekdong Cha, and Jeha Ryu. "Calibration and evaluation for visuo-haptic collocation in haptic augmented virtuality systems."  International Journal of Control, Automation and Systems  18.5 (2020): 1335-1342.

과제
"플랜트연구사업", 국토교통부/연구개발사업, 2016/03~2019/03
"스마트하지재활을 위한 인공지능", 과학기술정보통신부/ICT R&D 혁신 바우처 지원사업, 2020/03~2021/12