Research Topics
Research Topics
Embedded Files
- On-Device AI Agents
Efficient and Personalized AI Agents on various devices (Robots, Smartphones, Vehicles, Home Appliances, etc.)
Resource-Efficient Agent Architectures
On-Device Reasoning and Planning
Multimodal Perception for On-device AI Agents
Continual Learning for On-Device Agents
Efficient Agent Memory Systems
Energy-Aware Agent Intelligence
Multi-Agent Collaboration on Edge Devices
Real-Time Interactive Agents
Applications of On-Device AI Agents
- Embedded Physical AI (Embedded AI + Physical AI)
Intelligent On-device Systems for Physical Entities (Robots)
Efficient Learning for Embedded Physical AI
Self-Supervised Learning from Physical Signals
On-Device Multimodal Physical Perception
Adaptive and Continual Learning on Devices
Resource-Aware Physical AI Algorithms
Physical Interaction Intelligence
Embedded AI Systems and Platforms
- Embedded AI (On-Device AI & On-Device Machine Learning)
Efficient Deep Learning Inference, Training, and Adaptation
Embedded Computer Vision, NLP (Natural Language Processing), Reinforcement Learning, Multitask Learning, and Meta Learning
On-Device Interpretable and Explainable AI (XAI)
On-Device Neural Architecture Search (On-Device NAS)
Generative AI on Embedded Systems (Image/Video Generation and Language Models)
On-device Time-series Data Learning
On-Device Self-Supervised Learning and Continual Learning
Online Dataset Adaptation and Neural Architecture Search
Real-time Machine Learning
[On-device Sora] Mobile-Oriented Video Diffusion: Enabling Text-to-Video Generation on Mobile Devices Without Retraining, Compression, or Pruning (WACV 2026)
AliO: Output Alignment Matters in Long-Term Time Series Forecasting (NeurIPS 2025)
Position: The AI Conference Peer Review Crisis Demands Author Feedback and Reviewer Rewards (ICML 2025)
ICML 2025 Outstanding Position Paper Award (Top 0.55%)
TransPL: VQ-Code Transition Matrices for Pseudo-Labeling of Time Series Unsupervised Domain Adaptation (ICML 2025)
Smart ECU: Scalable On-Vehicle Deployment of Drivetrain Fault Classification Systems for Commercial Electric Vehicles (CIKM 2025)
PPT: Patch Order Do Matters In Time Series Pretext Task (ICLR 2025)
SMMF: Square-Matricized Momentum Factorization for Memory-Efficient Optimization (AAAI 2025)
Designing Extremely Memory-Efficient CNNs for On-device Vision Tasks (ACCV 2024)
ACCV 2024 Best Application Paper Award (Top 0.72%)
CAFO: Feature-Centric Explanation on Time Series Classification (KDD 2024)
Best Poster Award (2024 UNIST AI Technology Open Workshop)
On-NAS: On-Device Neural Architecture Search on Memory-Constrained Intelligent Embedded Systems (SenSys 2023)
Softmax Output Approximation for Activation Memory-Efficient Training of Attention-based Networks (NeurIPS 2023)
MicroDeblur: Image Motion Deblurring on Microcontroller-based Vision Systems (IPSN 2023)
IPSN 2023 Best Paper Runner-Up Award
Fast and Scalable In-memory Deep Multitask Learning via Neural Weight Virtualization (MobiSys 2020)
Weight Separation for Memory-Efficient and Accurate Deep Multitask Learning (PerCom 2022)
Deep Functional Network (DFN): Functional Interpretation of Deep Neural Networks for Intelligent Sensing Systems (IPSN 2021)
- Embedded, Real-Time, and Sensing Systems
Real-time Inference and Training of Machine Learning Algorithms
Intelligent Robot Systems
Smart Sensing Systems
SubFlow: A Dynamic Induced-Subgraph Strategy Toward Real-Time DNN Inference and Training (RTAS 2020)
- Collaborative, Collective, and Federated Learning
Multi-Device, Multi-Sensing, and Multi-Modal Learning
Distributed Learning
Intermittent (Battery-less) Computing
On-Demand Federated Learning for Arbitrary Target Class Distributions (AISTATS 2024)
Intermittent Learning: On-Device Machine Learning on Intermittently Powered System (IMWUT 2019/UbiComp 2020)
UbiComp 2020 Best Presentation Award
- AIoT (AI + IoT) and Intelligent Edge
Connected and Networked Intelligence
Beyond Communication: On-Modem DNN Inference and Training for Home Appliances (PerCom 2026)
Learning in the Wild: When, How, and What to Learn for On-Device Dataset Adaptation (AIChallengeIoT 2020)
AIChallengeIoT 2020 Best Paper Award
- Deep Learning Compilers
Generation and Optimization of Efficient Program Code and Executable Binary for Deep Learning Models
Bayesian Code Diffusion for Efficient Automatic Deep Learning Program Optimization (OSDI 2025)
- Mobile Computing and Smart Sensing Systems
AI and Machine Learning on Microcontrollers with Extreme Resource Constraints
Neuro.ZERO: A Zero-Energy Neural Network Accelerator for Embedded Sensing and Inference Systems (SenSys 2019)
- Cyber-Physical Systems
Deep Controller Theory
Knowledge Transfer Between Embedded Controllers (DCOSS 2018)
- Neural Memory
Next-generation Neural Memory Architectures and Algorithms
Neural Memory for Machine Reasoning and Artificial General Intelligence
- Confidential On-Device Deep Learning and Machine Learning
Enabling secure and confidential deep learning (machine learning) on resource-constrained embedded/mobile/IoT devices
Page updated
Google Sites
Report abuse