I am a Research Scientist at Samsung AI Center-Cambridge working with Dr Stylianos I. Venieris. Prior to that, I have obtained a PhD from the University of Cambridge under Prof. Cecilia Mascolo. My research bridges machine learning and systems through innovative on-device AI processing techniques, successfully commercialising breakthrough technologies like on-device diffusion models for various flagship Samsung smartphones (Galaxy S24, S25, Z Flip6 & Fold6, Z Flip7 & Fold7) that impact millions of users.

Recently recognised as an ML and Systems Rising Star by MLCommons, my work has earned consecutive Samsung Best Paper Silver Awards (2024, 2025) and Best Paper Award at SEC '21 , with publications in AI (ICML, NeurIPS, ICLR, and AAAI) and Systems (SenSys, IPSN, TMC, MobiCom, and IMWUT). I develop resource-efficient solutions that make advanced AI accessible on everyday devices with strict hardware constraints.

Research Focus:

  • Efficient Generative AI Systems: Reimagining resource-intensive generative models for mobile devices
  • On-Device Training & Continual Adaptation: Enabling devices to learn locally with minimal data, preserving privacy and improving personalisation
  • System-Algorithm Co-Design for IoT: Creating optimised solutions that synergise hardware capabilities and algorithmic innovations for resource-constrained environments


Want to Collaborate?
If you're interested in working with me, please contact me so we can have a chat.
I always love to interact and collaborate with brilliant minds.

Contact Info

youngkwon311<at>gmail.com
Google Scholar
GitHub
LinkedIn

News & Travel

(View All)

AI Products
Personalised On-Device AI Wallpaper
Featured at the Samsung Galaxy Unpacked Event. Dedicated YouTube Video showcasing this specific technology exceeded 390,000 views, while short-form content generated 28,000+ likes, demonstrating significant market interest and technological impact.
Galaxy S24 & S25, Z Flip6 & Fold6 & Flip7 & Fold7 | Samsung Galaxy Unpacked Event | Shorts (KR) | Shorts (EN) | YouTube (KR) | YouTube (EN)
Efficient On-Device Super Resolution
Enabled an extremely efficient on-device super-resolution, delivering superior image quality enhancement while significantly reducing computational requirements. This technology was successfully commercialised on Samsung's flagship Galaxy S25 smartphone and featured in official Samsung promotional materials.
Galaxy S25 Series | YouTube

Preprints
Speculative Decoding with a Speculative Vocabulary
Miles Williams, Young D. Kwon, Rui Li, Alexandros Kouris, and Stylianos I. Venieris
arXiv 2026 | PDF | Link
Tempora: Characterising the Time-Contingent Utility of Online Test-Time Adaptation
Sudarshan Sreeram, Young D. Kwon, and Cecilia Mascolo
arXiv 2026 | PDF | Link
Efficient High-Resolution Image Editing with Hallucination-Aware Loss and Adaptive Tiling
Young D. Kwon, Abhinav Mehrotra, Malcolm Chadwick, Albert Gil Ramos, and Sourav Bhattacharya
arXiv 2025 | PDF | Link
Samsung Best Paper Silver Award 2025
On-demand Test-time Adaptation for Edge Devices
Xiao MA, Young D. Kwon, and Dong MA
arXiv 2025 | PDF | Link
MetaCLBench: Meta Continual Learning Benchmark on Resource-Constrained Edge Devices
Young D. Kwon*, Sijia Li*, Lik-Hang Lee, and Pan Hui
arXiv 2025 | PDF | Link | * Co-first authors
LeanTTA: A Backpropagation-Free and Stateless Approach to Quantized Test-Time Adaptation on Edge Devices
Cynthia Dong, Hong Jia, Young D. Kwon, Georgios Rizos, and Cecilia Mascolo
arXiv 2025 | PDF | Link

Selected Publications
Architecture-Agnostic Test-Time Adaptation via Backprop-Free Embedding Alignment
Xiao Ma, Young D. Kwon, Pan Zhou, and Dong Ma
ICLR 2026 | PDF | BibTex | Link | Code
HierarchicalPrune: Position-Aware Compression for Large-Scale Diffusion Models
Young D. Kwon*, Rui Li*, Sijia Li, Da Li, Sourav Bhattacharya, and Stylianos Venieris
AAAI 2026 | PDF | Poster | Slides | BibTex | Link | * Co-first authors
Full Paper Acceptance Rate: 17.5%
TinyTrain: Resource-Aware Task-Adaptive Sparse Training of DNNs at the Data-Scarce Edge
Young D. Kwon, Rui Li, Stylianos I. Venieris, Jagmohan Chauhan, Nicholas D. Lane, and Cecilia Mascolo
ICML 2024 | PDF | Poster | Slides | BibTex | Link
Samsung Best Paper Silver Award 2024
TinyTTA: Efficient Test-time Adaptation via Early-exit Ensembles on Edge Devices
Hong Jia, Young D. Kwon, Alessio Orsino, Ting Dang, Domenico Talia, and Cecilia Mascolo
NeurIPS 2024 | PDF | Poster | Slides | BibTex | Link | Code
UR2M: Uncertainty and Resource-Aware Event Detection on Microcontrollers
Hong Jia, Young D. Kwon, Dong Ma, Nhat Pham, Lorena Qendro, Tam Vu, and Cecilia Mascolo
PerCom 2024 | PDF | BibTex
Oral Presentation, Full Paper Acceptance Rate: 14.5%
LifeLearner: Hardware-Aware Meta Continual Learning System for Embedded Computing Platforms
Young D. Kwon, Jagmohan Chauhan, Hong Jia, Stylianos I. Venieris, and Cecilia Mascolo
SenSys 2023 | PDF | BibTex
Oral Presentation, Full Paper Acceptance Rate: 18.9%
YONO: Modeling Multiple Heterogeneous Neural Networks on Microcontrollers
Young D. Kwon, Jagmohan Chauhan, and Cecilia Mascolo
IPSN 2022 | PDF | BibTex | Link
PROS: an Efficient Pattern-Driven Compressive Sensing Framework for Low-Power Biopotential-based Wearables with On-chip Intelligence
Nhat Pham, Hong Jia, Minh Tran, Tuan Dinh, Nam Bui, Young D. Kwon , Dong Ma, VP Nguyen, Cecilia Mascolo, Tam Vu
MobiCom 2022 | PDF | BibTex | Link
Oral Presentation, Full Paper Acceptance Rate: 17.8%
MyoKey: Inertial Motion Sensing and Gesture-based QWERTY Keyboard for Extended Realities
Kirill A. Shatilov, Young D. Kwon, Lik-Hang Lee, Dimitris Chatzopoulos, and Pan Hui
TMC 2022 | PDF | BibTex | Link
ContAuth: Continual Learning Framework for Behavioral-based User Authentication
Jagmohan Chauhan, Young D. Kwon, Pan Hui, and Cecilia Mascolo
IMWUT/UbiComp 2021 | PDF | BibTex | Link
FastICARL: Fast Incremental Classifier and Representation Learning with Efficient Budget Allocation in Audio Sensing Applications
Young D. Kwon, Jagmohan Chauhan, and Cecilia Mascolo
Interspeech 2021 | PDF | BibTex | Link
Exploring System Performance of Continual Learning for Mobile and Embedded Sensing Applications
Young D. Kwon, Jagmohan Chauhan, Abhishek Kumar, Pan Hui, and Cecilia Mascolo
SEC 2021 | PDF | BibTex | Link
Best Paper Award (Photo)

Professional Experiences

Samsung AI Center-Cambridge
Research Scientist · Oct. 2025 ~ Present
Advisor: Dr Stylianos I. Venieris
Research Scientist · Sep. 2023 ~ Sep. 2025
Advisor: Dr Stylianos I. Venieris and Dr Sourav Bhattacharya
Research Intern · Apr. 2022 ~ Apr. 2023
Advisor: Dr Stylianos I. Venieris, Dr Rui Li, Prof. Nicholas D. Lane

Computer Laboratory, University of Cambridge
ML Developer · Jul. 2020 ~ Sep. 2020
Advisor: Dr Jagmohan Chauhan and Prof. Cecilia Mascolo

Dept. of CSE, HKUST
Research Assistant · Mar. 2020 ~ Jun. 2020
Advisor: Prof. Dimitris Papadias

Memory Business, Samsung Electronics
Engineer · Jul. 2016 ~ Aug. 2017
Engineering Intern · Jul. 2015 ~ Aug. 2015

1st Fighter Wing, Republic of Korea Air Force
Staff Sergeant · Feb. 2011 ~ Feb. 2013


Honors & Awards
  • 2025
    ML and Systems Rising Star Award 2025 by MLCommons
  • 2025
    Silver Medal at Samsung Best Paper Award 2025
  • 2024
    Silver Medal at Samsung Best Paper Award 2024
  • 2021
    Best Paper Award at SEC 2021
  • 2020-2023
    Nokia Bell Labs Studentship for PhD Study at the University of Cambridge
  • 2017-2019
    The Postgraduate Studentship for MPhil Study at HKUST
  • 2014-2016
    Samsung Scholarship for Undergraduate Study at SKKU
  • 2010-2013
    National Science and Engineering Undergraduate Scholarship at SKKU
  • 2016
    Honorable Mention at the KIISE conference 2016
  • 2015
    Honorable Mention for undergraduate papers at the KIISE conference 2015
  • 2021
    Travel Grant from SEC
  • 2021
    Interspeech Travel Grant from ISCA
  • 2019
    The Research Travel Grant from HKUST
  • 2016
    Honored to be a Valedictorian in the college of ICE
  • 2016
    Excellent Record Award for Top 3 Graduates in the college of ICE
  • 2016
    Outstanding Undergraduate FYP Award in the college of ICE
  • 2015
    The Excellence Award in Mobile App Competition
  • 2013-2016
    SungKyunKwan University Scholarship for Excellent Records
  • 2013-2015
    Dean's List Awards, 4 times at SKKU and once at HKUST

Research Experiences

Optimising DNN Processing on Extremely Resource-Limited Devices
Research Intern (Advisor: Dr Stylianos I. Venieris, Dr Rui Li, and Prof. Nicholas D. Lane ) · Apr. 2022 ~ Apr. 2023

Incremental Learning on Resource-constrained Devices
Research Assistant (Advisor: Dr Jagmohan Chauhan and Prof. Cecilia Mascolo ) · Jul. 2020 ~ Sep. 2020

A Study of Applying Neural Networks on a Database
Research Assistant (Advisor: Prof. Dimitris Papadias ) · Feb. 2020 ~ Jun. 2020

Computer Laboratory at the University of Cambridge
Visiting Research Student (Advisor: Dr Jagmohan Chauhan and Prof. Cecilia Mascolo ) · Jul. 2019 ~ Dec. 2019

User Engagement Analysis and Churn Prediction with LBSN Datasets
Postgraduate Research Student (Advisor: Prof. Raymond Wong and Prof. Pan Hui) · Aug. 2018 ~ May. 2019

HKUST-DT System and Media Laboratory at HKUST
Postgraduate Research Student (Advisor: Prof. Pan Hui) · Aug. 2017 ~ Jan. 2020

Information & Intelligence System Lab. at SKKU
Research Intern (Advisor: Prof. Jee-Hyong Lee) · Sep. 2015 - June. 2016

Social Network Analysis Project with Social-Attribute Network Dataset of Google+
Undergraduate Research Student (Advisor: Prof. Pan Hui) · Feb. 2015 ~ June. 2015


Teaching Experiences

Mentorship

  •  •  Anish Krishna Vallapuram (M.Phil. at HKUST, co-supervised by Prof. Pan Hui, now at Amazon)
        Topic: Causal analysis on the anchor store effect in LBSNs and efficient federated learning
  •  •  Nikhil Nanda (B.S. at HKUST, co-supervised by Prof. Pan Hui, now at Columbia University)
        Topic: Interpretable business survival prediction
  •  •  Liang-yu Chen (B.S. at HKUST, co-supervised by Prof. Pan Hui, now at Purdue University)
        Topic: Interpretable attention network for churn prediction in LBSNs
  •  •  Yutong Chen (B.S. at HKUST, co-supervised by Prof. Pan Hui, now at the University of Chicago)
        Topic: Interpretable churn prediction in LBSNs
  •  •  Youwen Kang (B.S. at HKUST, co-supervised by Prof. Pan Hui, now at Tencent)
        Topic: Interpretable churn prediction in LBSNs
  •  •  Anish Das (M.Phil. at the University of Cambridge, co-supervised by Prof. Cecilia Mascolo, now at Goldman Sachs)
        Topic: Mobile GPU-based training
  •  •  Nav Leelarathna (B.S. at the University of Cambridge, co-supervised by Prof. Cecilia Mascolo)
        Topic: Optimizing on-device training on mobile devices
  •  •  Issam Nedjai (M.Phil. at the University of Cambridge, co-supervised by Prof. Abhirup Ghosh and Prof. Cecilia Mascolo)
        Topic: Gossip learning on mobile devices
  •  •  Cynthia X. Dong (M.Phil. at the University of Cambridge, co-supervised by Prof. Cecilia Mascolo, now at the University of Washington)
        Topic: Efficient and robust test-time adaptation
  •  •  Sijia Li (M.Phil. at HKUST, co-supervised by Prof. Lik-Hang Lee and Prof. Pan Hui)
        Topic: Meta-continual learning in mobile sensing applications
  •  •  Alessio Orsino (Ph.D. at the University of Calabria, co-supervised by Prof. Domenico Talia and Prof. Cecilia Mascolo)
        Topic: On-device training and efficient test-time adaptation
  •  •  Xiao Ma (Ph.D. at Singapore Management University, co-supervised by Prof. Dong Ma)
        Topic: On-demand test-time adaptation
  •  •  Francesco Corti (Ph.D. at the Graz University of Technology, co-supervised by Prof. Olga Saukh and Prof. Cecilia Mascolo)
        Topic: Sample-efficient test-time adaptation
  •  •  Sudarshan Sreeram (Ph.D. at the University of Cambridge, co-supervised by Prof. Cecilia Mascolo)
        Topic: Efficient and reliable inference and test-time adaptation on edge devices
  •  •  Miles Williams (Ph.D. at the University of Sheffield, co-supervised by Dr. Stylianos I. Venieris, now at SAIC-Cambridge)
        Topic: Accelerating LLMs via speculative decoding
  •  •  Oszkár Urbán (M.Phil. at the University of Cambridge, co-supervised by Prof. Cecilia Mascolo)
        Topic: Accelerating reasoning LLMs via efficient speculative decoding
  •  •  Michal Danilowski (Ph.D. at the University of Birmingham, co-supervised by Prof. Abhirup Ghosh)
        Topic: Continual and efficient test-time adaptation on-device

Teaching Assistant


Talks
  • [AAAI 2026][24 Jan 2026] HierarchicalPrune: Position-Aware Compression for Large-Scale Diffusion Models.
  • [ML & Systems Rising Stars Forum][9 May 2025] AI at the Edge: From Training to Generation. Host: Prof. Abdulrahman Mahmoud.
  • [ICML 2024][23 Jul 2024] TinyTrain: Resource-Aware Task-Adaptive Sparse Training of DNNs at the Data-Scarce Edge [Link].
  • [PerCom 2024][12 Mar 2024] UR2M: Uncertainty and Resource-Aware Event Detection on Microcontrollers. Host: Prof. Christine Julien
  • [EfficientML Reading Group][13 Feb 2024] Efficient Continual and On-Device Learning for Edge Computing Platforms. Host: Prof. Olga Saukh
  • [SenSys 2023][14 Nov 2023] LifeLearner: Hardware-Aware Meta Continual Learning System for Embedded Computing Platforms. Host: Dr Tarek Abdelzaher
  • [SenSys 2023][12 Nov 2023] On-device Training at the Extreme Edge. Host: Dr Stephen Xia
  • [Cambridge Korea Academic Society][25 Mar 2023] Deep Learning at the Extreme Edge. Host: Dr Gwangbin Bae
  • [Korea Military Academy][4 Feb 2022] YONO: All You Need To Represent Multiple Dissimilar Neural Networks on Microcontrollers. Host: Prof. Juhee Kim
  • [KAIST][27 Jan 2022] On-device Continual Learning in Mobile Sensing Applications. Host: Prof. Lik-Hang Lee
  • [KAIST][27 Jan 2022] You Only Need One Pair of Codebooks to Represent Multiple Deep Learning Models on Extremely Resouce-Constrained Devices. Host: Prof. Junehwa Song
  • [University of Cambridge][12 Aug 2021] Efficient Continual Learning in Mobile Sensing Applications. Host: Prof. Nicholas D. Lane
  • [University of Cambridge][3 Dec 2019] An Empirical Study of Lifelong Learning on Mobile Applications. Host: Dr Seyyed Ahmad Javadi
  • [Korea Military Academy][8 Oct 2018] Characterization and Prediction of Churning Users in CQAs and LBSNs. Host: Prof. Seonho Lee
  • [HKUST][5 Jul 2018] Community effects on Self-Disclosure Behaviors of Users in an Online Social Network. Host: Prof. Pan Hui

Selected Fun Projects

Professional Service

Committee

Reviewer

Student Volunteer


Misc.

Extra Activities

Rowing - Won silver medal in HKUST Indoor Rowing Competition in Apr 2015 | photo
Rowing - Won bronze medal in 2015 Hong Kong China Rowing Association Coastal Rowing Championships in Mar 2015 | photo
Marathon - Completed half marathon (21.1km) 2 times in 2013 and 2014 (photo)


Traveling

I love traveling to new places since I can meet entirely new people with different perspectives towards lives, worlds, etc.
You can check countries I have visited here in this web page


Site Statistics

Visitor Counts


Enabled by Hitwebcounter.com