Seulki Lee

Orcid: 0009-0004-7162-0845

Affiliations:
  • Ulsan National Institute of Science and Technology, South Korea
  • University of North Carolina at Chapel Hill, NC, USA (PhD 2021)


According to our database1, Seulki Lee authored at least 20 papers between 2018 and 2025.

Collaborative distances:
  • Dijkstra number2 of five.
  • Erdős number3 of five.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2025
On-device Sora: Enabling Diffusion-Based Text-to-Video Generation for Mobile Devices.
CoRR, February, 2025

Bayesian Code Diffusion for Efficient Automatic Deep Learning Program Optimization.
Proceedings of the 19th USENIX Symposium on Operating Systems Design and Implementation, 2025

SMMF: Square-Matricized Momentum Factorization for Memory-Efficient Optimization.
Proceedings of the AAAI-25, Sponsored by the Association for the Advancement of Artificial Intelligence, February 25, 2025

2024
CAFO: Feature-Centric Explanation on Time Series Classification.
Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2024

On-Demand Federated Learning for Arbitrary Target Class Distributions.
Proceedings of the International Conference on Artificial Intelligence and Statistics, 2024

Designing Extremely Memory-Efficient CNNs for On-Device Vision Tasks.
Proceedings of the Computer Vision - ACCV 2024, 2024

2023
Multitask Deep Learning for Human Activity, Speed, and Body Weight Estimation Using Commercial Smart Insoles.
IEEE Internet Things J., September, 2023

On-NAS: On-Device Neural Architecture Search on Memory-Constrained Intelligent Embedded Systems.
Proceedings of the 21st ACM Conference on Embedded Networked Sensor Systems, 2023

Softmax Output Approximation for Activation Memory-Efficient Training of Attention-based Networks.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

MicroDeblur: Image Motion Deblurring on Microcontroller-based Vision Systems.
Proceedings of the 22nd International Conference on Information Processing in Sensor Networks, 2023

2022
Weight Separation for Memory-Efficient and Accurate Deep Multitask Learning.
Proceedings of the IEEE International Conference on Pervasive Computing and Communications, 2022

2021
Enabling Deep Intelligence on Embedded Systems.
PhD thesis, 2021

Deep Functional Network (DFN): Functional Interpretation of Deep Neural Networks for Intelligent Sensing Systems.
Proceedings of the IPSN '21: The 20th International Conference on Information Processing in Sensor Networks, 2021

2020
Learning in the Wild: When, How, and What to Learn for On-Device Dataset Adaptation.
Proceedings of the AIChallengeIoT@SenSys 2020: Proceedings of the 2nd International Workshop on Challenges in Artificial Intelligence and Machine Learning for Internet of Things, 2020

SubFlow: A Dynamic Induced-Subgraph Strategy Toward Real-Time DNN Inference and Training.
Proceedings of the IEEE Real-Time and Embedded Technology and Applications Symposium, 2020

Fast and scalable in-memory deep multitask learning via neural weight virtualization.
Proceedings of the MobiSys '20: The 18th Annual International Conference on Mobile Systems, 2020

2019
Intermittent Learning: On-Device Machine Learning on Intermittently Powered System.
Proc. ACM Interact. Mob. Wearable Ubiquitous Technol., 2019

Neuro.ZERO: a zero-energy neural network accelerator for embedded sensing and inference systems.
Proceedings of the 17th Conference on Embedded Networked Sensor Systems, 2019

On-device training from sensor data on batteryless platforms: poster abstract.
Proceedings of the 18th International Conference on Information Processing in Sensor Networks, 2019

2018
Knowledge Transfer Between Embedded Controllers.
Proceedings of the 14th International Conference on Distributed Computing in Sensor Systems, 2018


  Loading...