Xiangzhong Luo @ SEU

Biography

I am now a Tenure-Track Associate Professor at PALM Lab, the School of Computer Science and Engineering, Southeast University (SEU), China. From 2024 to 2025, I was a Research Fellow at Nanyang Technological University (NTU), Singapore, where I worked with Prof. Rui Tan. Before that, I received my Ph.D. degree from NTU in 2023 under the supervision of Prof. Weichen Liu and my B.S. degree from Shanghai Jiao Tong University (SJTU) in 2019, respectively.

News

For self-motivated undergraduates/masters, please feel free to email me with your CV (also check this link).

Research Interests

Efficient AI Algorithms
Efficient Large Language Models
Neural Architecture Search
Model Compression

Publications

Book Chapters

Edge Intelligence: From Deep Learning’s Perspective

D. Liu, H. Kong, X. Luo, S. Huai, and W. Liu.
The Key Elements of Digital Factory, Elsevier, 2024.

Journal Papers

Efficient Deep Learning Infrastructures for Embedded Computing Systems: A Comprehensive Survey and Future Envision

X. Luo, D. Liu, H. Kong, S. Huai, H. Chen, G. Xiong, and W. Liu.
ACM Transactions on Embedded Computing Systems (TECS), 2024.

Domino-Pro-Max: Towards Efficient Network Simplification and Reparameterization for Embedded Hardware Systems

X. Luo, D. Liu, H. Kong, S. Huai, G. Xiong, and W. Liu.
IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD), 2024.

EvoLP: Self-Evolving Latency Predictor for Model Compression in Real-Time Edge Systems

S. Huai, H. Kong, S. Li, X. Luo, R. Subramaniam, C. Makaya, Q. Lin, and W. Liu.
IEEE Embedded Systems Letters (ESL), 2024.

LightNAS: On Lightweight and Scalable Neural Architecture Search for Embedded Platforms

X. Luo, D. Liu, H. Kong, S. Huai, H. Chen, and W. Liu.
IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD), 2023.

EdgeCompress: Coupling Multi-Dimensional Model Compression and Dynamic Inference for EdgeAI

H. Kong, D. Liu, S. Huai, X. Luo, R. Subramaniam, C. Makaya, Q. Lin, and W. Liu.
IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD), 2023.

SurgeNAS: A Comprehensive Surgery on Hardware-Aware Differentiable Neural Architecture Search

X. Luo, D. Liu, H. Kong, S. Huai, H. Chen, and W. Liu.
IEEE Transactions on Computers (TC), 2023.

On Hardware-Aware Design and Optimization of Edge Intelligence

S. Huai*, H. Kong*, X. Luo*, D. Liu, R. Subramaniam, C. Makaya, Q. Lin, and W. Liu.
IEEE Design & Test, 2023.

CRIMP: Compact & Reliable DNNs Inference for In-Memory Processing via Crossbar-Aligned Compression and Non-ideality Adaptation

S. Huai, H. Kong, X. Luo, S. Li, R. Subramaniam, C. Makaya, Q. Lin, and W. Liu.
ACM Transactions on Embedded Computing Systems (TECS), 2023.

Designing Efficient DNNs via Hardware-Aware Neural Architecture Search and Beyond

X. Luo, D. Liu, S. Huai, H. Kong, H. Chen, and W. Liu.
IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD), 2022.

Bringing AI To Edge: From Deep Learning's Perspective

D. Liu*, H. Kong*, X. Luo*, W. Liu, and R. Subramaniam.
Elsevier Neurocomputing, 2022.

LAMP: Load-balanced Multipath Parallel Transmission in Point-to-point NoCs

H. Chen, P. Chen, X. Luo, S. Huai, and W. Liu.
IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD), 2022.

MARCO: A High-performance Task Mapping and Routing Co-optimization Framework for Point-to-Point NoC-based Heterogeneous Computing Systems

H. Chen, Z. Zhang, P. Chen, X. Luo, S. Li, and W. Liu.
ACM Transactions on Embedded Computing Systems (TECS), 2021.

Conference Papers

Mobile Vision Dynamic Layer Dropping Against Adversarial Attacks

Z. Ma, X. Luo, Q. Song, and R. Tan.
ACM Conference on Embedded Networked Sensor Systems (SenSys) Demo, 2025.

Parameterized Stochastic Ensemble Defense for Object Detection

Y. Wu, D. Guo, X. Luo, Q. Song, and R. Tan.
ACM Conference on Embedded Networked Sensor Systems (SenSys) Poster, 2025.

Double-Win NAS: Towards Deep-to-Shallow Transformable Neural Architecture Search for Intelligent Embedded Systems

X. Luo, D. Liu, H. Kong, S. Huai, and W. Liu.
ACM/IEEE Design Automation Conference (DAC), 2024.

Pearls Hide Behind Linearity: Simplifying Deep Convolutional Networks for Embedded Hardware Systems via Linearity Grafting

X. Luo, D. Liu, H. Kong, S. Huai, H. Chen, S. Li, G. Xiong, and W. Liu.
ACM/IEEE Asia and South Pacific Design Automation Conference (ASP-DAC), 2024.

An Efficient Sparse LSTM Accelerator on Embedded FPGAs with Bandwidth-oriented Pruning

S. Li, S. Zhu, X. Luo, T. Luo, and W. Liu.
IEEE International Conference on Field-Programmable Logic and Applications (FPL), 2023.

Towards Efficient Convolutional Neural Network for Embedded Hardware via Multi-Dimensional Pruning

H. Kong, D. Liu, X. Luo, S. Huai, R. Subramaniam, C. Makaya, Q. Lin, and W. Liu.
ACM/IEEE Design Automation Conference (DAC), 2023.

EMNAPE: Efficient Multi-Dimensional Neural Architecture Pruning for EdgeAI

H. Kong, X. Luo, S. Huai, D. Liu, R. Subramaniam, C. Makaya, Q. Lin, and W. Liu.
Design, Automation and Test in Europe (DATE), 2023.

MUGNoC: A Software-configured Multicast-Unicast-Gather NoC for Accelerating CNN Dataflows

H. Chen, D. Liu, S. Li, S. Huai, X. Luo, and W. Liu.
ACM/IEEE Asia and South Pacific Design Automation Conference (ASP-DAC), 2023.

Crossbar-Aligned & Integer-Only Neural Network Compression for Efficient In-Memory Acceleration

S. Huai, D. Liu, X. Luo, H. Chen, W. Liu, and R. Subramaniam.
ACM/IEEE Asia and South Pacific Design Automation Conference (ASP-DAC), 2023.

You Only Search Once: On Lightweight Differentiable Architecture Search for Resource-Constrained Embedded Platforms

X. Luo, D. Liu, H. Kong, S. Huai, H. Chen, and W. Liu.
ACM/IEEE Design Automation Conference (DAC), 2022.

Smart Scissor: Coupling Spatial Redundancy Reduction and CNN Compression for Embedded Hardware

H. Kong, D. Liu, S. Huai, X. Luo, W. Liu, R. Subramaniam, C. Makaya, and Q. Lin.
ACM/IEEE International Conference on Computer Aided Design (ICCAD), 2022.

What to Expect of Early Training Statistics? An Investigation on Hardware-Aware Neural Architecture Search: Work-in-Progress

X. Luo, D. Liu, H. Chen, H. Kong, S. Huai, and W. Liu.
ACM/IEEE International Conference on Hardware/Software Codesign and System Synthesis (CODES+ISSS), 2022.

Collate: Collaborative Neural Network Learning for Latency-Critical Edge Systems

S. Huai, D. Liu, H. Kong, X. Luo, W. Liu, R. Subramaniam, C. Makaya, and Q. Lin.
IEEE International Conference on Computer Design (ICCD), 2022.

HACScale: Hardware-Aware Compound Scaling for Resource-Efficient DNNs

H. Kong, D. Liu, X. Luo, W. Liu, and R. Subramaniam.
ACM/IEEE Asia and South Pacific Design Automation Conference (ASP-DAC), 2022.

HSCoNAS: Hardware-Software Co-Design of Efficient DNNs via Neural Architecture Search

X. Luo, D. Liu, S. Huai, and W. Liu.
Design, Automation and Test in Europe (DATE), 2021.

EdgeNAS: Discovering Efficient Neural Architectures for Edge Systems

X. Luo, D. Liu, H. Kong, and W. Liu.
IEEE International Conference on Computer Design (ICCD), 2020.

Person Re-identification via Pose-aware Multi-semantic Learning

X. Luo, L. H. K. Duong, and W. Liu.
IEEE International Conference on Multimedia and Expo (ICME), 2020.

Selected Awards

HiPEAC Paper Award from European Network on High Performance, Edge, and Cloud Computing 2023
Publicity Paper Award from ACM/IEEE Design Automation Conference (DAC) 2022
Research Scholarship from Nanyang Technological University 2019-2023

A Collection of Useful Resources