Shun Lu 陆顺

PHD Candidate
Email: lushun901@gmail.com

        

News

Biography

Shun Lu holds a Bachelor's degree from Beijing University of Science and Technology (USTB) and I am currently a PhD student at the Institute of Computing Technology (ICT), advised by Yu Hu. My research focuses on the field of computer science, with a particular emphasis on developing algorithms to search for efficient models and compress models. I am passionate about exploring new approaches to these problems and have been fortunate enough to work on several exciting projects during my time at ICT. I am excited to continue my research in this field and to contribute to the advancement of computer science and technology.

My research interests include neural architecture search, model compression, audio separation, speaker verification, and semantic segmentation. Regarding neural architecture search, I am working on developing automated methods to design and optimize neural network architectures. This involves exploring different network topologies and architectures to find the optimal solution for a given task. I believe that this research will have significant impact on the development of artificial intelligence and machine learning, and I am excited to be a part of this exciting field.

Projects

alt text

StarLight: An Open-Source AutoML Toolkit for Lightweighting Deep Neural Networks
Shun Lu, Longxing Yang, Zihao Sun, Jilin Mei, Yu Hu*
[Code][Demo][Tutorial]

Selected Publications

alt text

PA&DA: Jointly Sampling Path and Data for Consistent NAS
Shun Lu, Yu Hu*, Longxing Yang, Zihao Sun, Jilin Mei, Jianchao Tan, Chengru Song
[CVPR 2023][Paper][Code]

alt text

PINAT: A Permutation INvariance Augmented Transformer for NAS Predictor
Shun Lu, Yu Hu*, Peihao Wang, Yan Han, Jianchao Tan, Jixiang Li, Sen Yang, Ji Liu
[AAAI 2023][Paper][Code]

alt text

Conformer Space Neural Architecture Search for Multi-Task Audio Separation
Shun Lu, Yang Wang, Peng Yao, Chenxing Li, Jianchao Tan, Feng Deng, Xiaorui Wang, Chengru Song
[Interspeech 2022][Paper]

alt text

DU-DARTS: Decreasing the Uncertainty of Differentiable NAS
Shun Lu, Yu Hu*, Longxing Yang, Zihao Sun, Jilin Mei, Yiming Zeng, Xiaowei Li
[BMVC 2021][Paper][Code]

alt text

TNASP: A Transformer-based NAS Predictor with a Self-evolution Framework
Shun Lu, Jixiang Li, Jianchao Tan, Sen Yang, Ji Liu
[NeurIPS 2021][Paper]

alt text

Searching for BurgerFormer with Micro-Meso-Macro Space Design
Longxing Yang, Yu Hu*, Shun Lu, Zihao Sun, Jilin Mei, Yinhe Han, Xiaowei Li
[ICML 2022][Paper][Code]

alt text

AGNAS: Attention-Guided Micro and Macro-Architecture Search
Zihao Sun, Yu Hu*, Shun Lu, Longxing Yang, Jilin Mei, Yinhe Han, Xiaowei Li
[ICML 2022][Paper][Code]

alt text

DDSAS: Dynamic and Differentiable Space-Architecture Search
Longxing Yang, Yu Hu*, Shun Lu, Zihao Sun, Jilin Mei, Yiming Zeng, Zhiping Shi, Yinhe Han, Xiaowei Li
[ACML 2021][Paper][Code]

alt text

SpeechNAS: Towards Better Trade-off between Latency and Accuracy for Large-Scale Speaker Verification
Wentao Zhu, Tianlong Kong, Shun Lu, Jixiang Li, Dawei Zhang, Feng Deng, Xiaorui Wang, Sen Yang, Ji Liu
[ASRU 2021][Paper][Code]

alt text

DARTS-: Robustly Stepping out of Performance Collapse Without Indicators
Xiangxiang Chu, Xiaoxing Wang, Bo Zhang, Shun Lu, Xiaolin Wei, Junchi Yan
[ICLR 2021][Paper][Code]

alt text

STC-NAS: Fast neural architecture search with source-target consistency
Zihao Sun, Yu Hu*, Longxing Yang, Shun Lu, Jilin Mei, Yinhe Han, Xiaowei Li
[Neurocomputing][Paper]

alt text

Dynamic coherent diffractive imaging with a physics-driven untrained learning method
Dongyu Yang, Junhao Zhang, Ye Tao, Wenjin Lv, Xinkai Sun, Shun Lu, Hao Chen, Wenhui Xu, Yishi Shi
[Optics Express][Paper]

alt text  

MixPath: A Unified Approach for One-shot Neural Architecture Search
Xiangxiang Chu, Xudong Li, Shun Lu, Bo Zhang, Jixiang Li
[arXiv 2020][Paper][Code]

Competitions

Academic Services

Honors and Awards

© Shun Lu | Last update: June 2023