Publication

Preprints

2025

• [arXiv] “On-device Sora: Enabling Diffusion-Based Text-to-Video Generation for Mobile Devices”

  • Feb, 2025. [pdf][code]

  • Bosung Kim*, Kyuhwan Lee*, Isu Jeong, Jungmin Cheon, Yeojin Lee, and Seulki Lee (*: Equal contribution)

• “Designing Extremely Memory-Efficient CNNs for On-device Vision and Audio Tasks”

  • Yoel Park, Jae Wook Lee, and Seulki Lee [pdf]

Conferences and Journals

2026

• (Submitted) [AISTATS 2026] “Anonymized”

  • Twenty-Ninth Annual Conference on Artificial Intelligence and Statistics, Tangier, Morocco, May 2026.

  • Changhyeon Lee and Seulki Lee

• (Submitted) [ICLR 2026] “Anonymized”

  • The Fourteenth International Conference on Learning Representations, Rio de Janeiro, Brazil, April 2026.

  • Jeongmin Cheon and Seulki Lee

• (Submitted) [ICLR 2026] “Anonymized”

  • The Fourteenth International Conference on Learning Representations, Rio de Janeiro, Brazil, April 2026.

  • Yunseok Lee and Seulki Lee

• (Submitted) [ICLR 2026] “Anonymized”

  • The Fourteenth International Conference on Learning Representations, Rio de Janeiro, Brazil, April 2026.

  • Heejung Shin, Jiwoo Kim, Seulki Lee, and Hyondong Oh

• (Submitted) [PerCom 2026] “Anonymized”

  • The 20th International Conference on Pervasive Computing and Communications, Pisa, Italy, Mar 2026.

  • Insung Jung and Seulki Lee

• (Submitted) [WACV 2026] “Anonymized”

  • The IEEE/CVF Winter Conference on Applications of Computer Vision 2026, Tucson, Arizona, Mar 2026.

  • Bosung Kim*, Kyuhwan Lee*, Isu Jeong, Jungmin Cheon, Yeojin Lee, and Seulki Lee (*: Equal contribution)

2025

• [NeurIPS 2025] “AliO: Output Alignment Matters in Long-Term Time Series Forecasting”

  • The Thirty-Ninth Annual Conference on Neural Information Processing Systems, San Diego, USA, Dec 2025.

  • Kwangryeol Park, Jaeho Kim, and Seulki Lee

• [IJCV] “Designing Extremely Memory-Efficient CNNs for On-device Vision and Auido Tasks”

  • International Journal of Computer Vision (IJCV), Springer Nature, 2025. To appear

  • Yoel Park, Jae Wook Lee, and Seulki Lee

•  [CIKM 2025] “Smart ECU: Scalable On-Vehicle Deployment of Drivetrain Fault Classification Systems for Commercial Electric Vehicles”

  • The 34th ACM International Conference on Information and Knowledge Management (Applied Research Track), Seoul, Korea, Nov 2025. To appear

  • Jaeho Kim*, Kwangryeol Park*, Kyu Hwan Lee*, Jeongmin Oh, Dongjin Park, Hyunseok Oh, Youngrock Chung, Kyung-Woo Lee, Dae-Un Sung, and Seulki Lee  (*: Equal contribution)

• [ICML 2025] “TransPL: VQ-Code Transition Matrices for Pseudo-Labeling of Time Series Unsupervised Domain Adaptation”

  • The Forty-Second International Conference on Machine Learning, Vancouver, Canada, July 2025. [pdf][code][video][poster]

  • Jaeho Kim and Seulki Lee

• [ICML 2025] “Position: The AI Conference Peer Review Crisis Demands Author Feedback and Reviewer Rewards”

  • The Forty-Second International Conference on Machine Learning, Vancouver, Canada, July 2025. [pdf][video][poster]

  • Jaeho Kim*, Yunseok Lee*, and Seulki Lee (*: Equal contribution) [Oral: 12/361=3.32%]

  • ICML 2025 Outstanding Position Paper Award (0.55%=2/361[position papers], 0.064%=(2+6)/(361+12,107)[entire papers]) [award][link]

• [OSDI 2025] “Bayesian Code Diffusion for Efficient Automatic Deep Learning Program Optimization”

  • The 19th USENIX Symposium on Operating Systems Design and Implementation, Boston, Massachusetts, USA, July 2025. [pdf][slides][code][video][poster]

  • Isu Jeong and Seulki Lee [14.2% = 48/338]

• [ICLR 2025] “PPT: Patch Order Do Matters In Time Series Pretext Task”

  • The Thirteenth International Conference on Learning Representations, Singapore, April 2025. [pdf][slides][code][video][poster]

  • Jaeho Kim*, Kwangryeol Park*, Sukmin Yun, and Seulki Lee (*: Equal contribution)

• [AAAI 2025] “SMMF: Square-Matricized Momentum Factorization for Memory-Efficient Optimization”

  • The 39th Annual AAAI Conference on Artificial Intelligence, Philadelphia, Pennsylvania, USA, Feb 2025. [pdf][slides][code][video][poster]

  • Kwangryeol Park and Seulki Lee

2024

• [ACCV 2024] “Designing Extremely Memory-Efficient CNNs for On-device Vision Tasks”

  • The 17th Asian Conference on Computer Vision, Hanoi, Vietnam, Dec 2024. [pdf][slides][video][poster]

  • Jae Wook Lee, Yoel Park, and Seulki Lee [Oral 0.72%]

  • ACCV 2024 Best Application Paper Award (Top 0.72%) [link][award]

• [IJHCS 2024] “Unpacking Instagram use: The impact of upward social comparisons on usage patterns and affective experiences in the wild”

  • International Journal of Human-Computer Studies, June 2024. [pdf]

  • Jiwan Kim, Doyoung Lee, Mingyu Han, Jaeho Kim, Vassilis Kostakos, Ian Oakley

• [KDD 2024] “CAFO: Feature-Centric Explanation on Time Series Classification”

  • The 30th SIGKDD Conference on Knowledge Discovery and Data Mining, Aug 2024, Barcelona, Spain, Aug 2024. [pdf][slides][code][video][poster]

  • Jaeho Kim, Seok-Ju Hahn, Yoontae Hwang, Junghye Lee, and Seulki Lee [Oral]

  • Best Poster Award (2024 UNIST AI Technology Open Workshop)

• [AISTATS 2024] “On-Demand Federated Learning for Arbitrary Target Class Distributions”

  • The 27th International Conference on Artificial Intelligence and Statistics, Valencia, Spain, May 2024. [pdf][code][video][poster]

  • Isu Jeong and Seulki Lee 

2023

• [NeurIPS 2023] “Softmax Output Approximation for Activation Memory-Efficient Training of Attention-based Networks”

  • The 37th Annual Conference on Neural Information Processing Systems, New Orleans, LA, USA, Dec 2023. [pdf][slides][code][talk(video)][poster]

  • Changhyeon Lee and Seulki Lee 

• [SenSys 2023] “On-NAS: On-Device Neural Architecture Search on Memory-Constrained Intelligent Embedded Systems”

  • The 21th ACM Conference on Embedded Networked Sensor Systems, Istanbul, Turkiye, Nov 2023. [pdf][slides][code][talk(video)]

  • Bosung Kim and Seulki Lee

• [IPSN 2023] "MicroDeblur: Image Motion Deblurring on Microcontroller-based Vision Systems"

  • The 22th International Conference on Information Processing in Sensor Networks, San Antonio, Texas, USA, May 2023. [pdf][slides]

  • Seulki Lee

  • IPSN 2023 Best Paper Runner Up Award

• [IEEE Internet of Things 2023] "Multitask Deep Learning for Human Activity, Speed, and Body Weight Estimation using Commercial Smart Insoles"

  • Proceedings of IEEE Internet of Things Journal, Apr 2023. [pdf]

  • Jaeho Kim, Hyewon Kang, Jaewan Yang, Haneul Jung, Seulki Lee, and Junghye Lee

2022

• [PerCom 2022] "Weight Separation for Memory-Efficient and Accurate Deep Multitask Learning"

  • The 20th International Conference on Pervasive Computing and Communications, Pisa, Italy, March 2022. [pdf][slides][talk(video)][code]

  • Seulki Lee and Shahriar Nirjon

2021

• [IPSN 2021] "Deep Functional Network (DFN): Functional Interpretation of Deep Neural Networks for Intelligent Sensing Systems"

  • The 20th International Conference on Information Processing in Sensor Networks, Nashville, USA, May 2021. [pdf][slides][talk(video)][code]

1. • Seulki Lee and Shahriar Nirjon

2020

• [AIChallengeIoT 2020] (Workshop) "Learning in the Wild: When, How, and What to Learn for On-Device Dataset Adaptation"

  • The 2nd International Workshop on Challenges in Artificial Intelligence and Machine Learning for Internet of Things, Virtual Event, Japan, November, 2020. [pdf][slides][talk(video)]

1. • Seulki Lee and Shahriar Nirjon

   • AIChallengeIoT 2020 Best Paper Award [award]

• [MobiSys 2020] "Fast and Scalable In-memory Deep Multitask Learning via Neural Weight Virtualization"

  • The 18th ACM International Conference on Mobile Systems, Applications, and Services, Toronto, Canada, June 2020. [pdf][slides][talk(video)][code]

1. • Seulki Lee and Shahriar Nirjon

• [RTAS 2020] "SubFlow: A Dynamic Induced-Subgraph Strategy Toward Real-Time DNN Inference and Training"

  • The 26th IEEE Real-Time and Embedded Technology and Applications Symposium, Sydney, Australia, April 2020. [pdf][slides][talk(video)][code]

1. • Seulki Lee and Shahriar Nirjon

2019

• [IMWUT 2019/UbiComp 2020] “Intermittent Learning: On-Device Machine Learning on Intermittently Powered System”

  • Proceedings of ACM on Interactive, Mobile, Wearable, and Ubiquitous Computing, Cancun, Mexico, September 2020. [pdf][slides][talk(video)][code]

1. • Seulki Lee, Bashima Islam, Yubo Luo, and Shahriar Nirjon

   • UbiComp 2020 Best Paper Presentation Award [award]

• [SenSys 2019] “Neuro.ZERO: A Zero-Energy Neural Network Accelerator for Embedded Sensing and Inference Systems”

  • The 17th ACM Conference on Embedded Networked Sensor Systems, New York, USA, November 2019. [pdf][slides][talk(video)][code]

1. • Seulki Lee and Shahriar Nirjon

• [RTAS 2019] (WIP) "Time-Aware Deep Intelligence on Batteryless Systems"

  • The 25th IEEE Real-Time and Embedded Technol-ogy and Applications Symposium, Montreal, Canada, April 2019. [pdf]

1. • Bashima Islam, Seulki Lee, and Shahriar Nirjon

• [IPSN 2019] (Poster) "On-device Training From Sensor Data on Batteryless Platforms"

  • The 18th International Conference on Information Processing in Sensor Networks, Montreal, Canada, April 2019. [pdf]

1. • Bahsima Islam, Yubo Luo, Seulki Lee, and Shahriar Nirjon

2018

• [DCOSS 2018] "Knowledge Transfer Between Embedded Controllers"

  • In the 14th International Conference on Distributed Computing in Sensor Systems, New York, USA, June 2018. [pdf][slides][demo(video)]

1. • Seulki Lee and Shahriar Nirjon

Honors and Awards

• Outstanding Position Paper Award

  • ICML 2025: Jaeho Kim*, Yunseok Lee*, and Seulki Lee ("Position: The AI Conference Peer Review Crisis Demands Author Feedback and Reviewer Rewards") [award][link]

• Best Paper Award

  • AIChallengeIoT 2020: Seulki Lee ("Learning in the Wild: When, How, and What to Learn for On-Device Dataset Adaptation") [award]

• Best Application Paper Award

  • ACCV 2024: Jae Wook Lee, Yoel Park, and Seulki Lee ("Designing Extremely Memory-Efficient CNNs for On-device Vision Tasks") [award][link]

• Best Paper Runner-Up Award

  • IPSN 2023: Seulki Lee ("MicroDeblur: Image Motion Deblurring on Microcontroller-based Vision Systems")

• Best Paper Presentation Award

• • • UbiComp 2020: Seulki Lee (“Intermittent Learning: On-Device Machine Learning on Intermittently Powered System”) [award]

  • Best Poster Award

    • 2024 UNIST AI Technology Open Workshop: Jaeho Kim ("CAFO: Feature-Centric Explanation on Time Series Classification")

  • Distinguished TCP Member Award

    • SenSys 2025: Seulki Lee [award]

  • 2024 Hyundai Mobis Edge AI Research Contest (2024 현대모비스 Edge AI 산학협력 연구공모)

    • Bosung Kim: 2nd Place Award

    • Jaeho Kim: 4th Place Award [link]

  • GCP (Google Cloud Platform) Credit Award: Gemma 2 Academic Program 2024

  • K-Data Science Conference 2024 Creative Researcher Award

    • Jaeho Kim: 3rd Place Award