Yang Sui | 隋阳

Howdy! I'm a Ph.D. student at Department of Electrical and Computer Engineering, Rutgers University, working on efficient AI, advised by Prof. Bo Yuan. I received my M.E. and B.E. at College of Electronic Science and Engineering, Jilin University.

Since February 2024, I joined the Creative Vision team, Snap Research as a Research Intern, working with Dr. Jian Ren, to explore efficient generative AI. During the 2023 Fall, I participated in the Princeton-Rutgers Exchange Program as a visiting student at Princeton University. From May 2022 to May 2023, I was a Research Intern at Media Lab, Tencent America, exploring efficiency and robustness of Learned Image Compression and Transformer models. In 2019, I was a full-time Algorithm Engineer at JD, working on the face verification and recognition. In 2018, I also spent a wonderful time as a Research and Development Intern and a member of PaddlePaddle (20.4k stars now), initializing the deep learning inference framework Paddle-Lite (6.6k stars now) at Baidu, reported in NeurIPS Expo, Baidu Create, Wave Summit+.

In addition to my academic work, I am passionate about Basketball, DOTA/DOTA2, World of Warcraft. I love Tracy McGrady, Stephen Curry, Lionel Messi, PIS (YaphetS). Join me for a game of basketball anytime.

I'm looking forward to the collaboration related to efficiency and security of deep learning. If you're interested in working with me, please don't hesitate to contact me.

Email  /  Google Scholar  /  Github   

My research is primarily focused on Efficient AI and Secure AI. In the domain of Efficient AI, my investigations revolve around developing techniques to achieve resource-efficient deep learning models without compromising their accuracy or performance. I aim to design and innovate compression methods, such as pruning, quantization, and low-rank approximation, to reduce the size and complexity of deep learning models. By doing so, I intend to facilitate the deployment of these models on resource-constrained devices like mobile phones and embedded systems. In my research on Secure AI, my interests lie in investigating the vulnerability and robustness through adversarial attacks and backdoor attacks. I am dedicated to understanding the vulnerabilities of AI models in the face of these malicious threats and develop defense mechanisms that enhance the robustness AI models against these attacks. Specifically, my research areas include:

• AI Efficiency: Model Compression & Data Compression.

• AI Security: Model Vulnerability & Robustness.

• Algorithm-hardware Co-design for AI Acceleration.

• Generative AI: Diffusion Model & Large Language Model.

• Supervised Learning on CNN and Transformer.

• Image Processing: Learned Image Compression.

• Digital Signal Processing: Error Correct Coding, Radio Frequency Neural Network.

Previous "Efficient Deep Learning Reading Group" Sessions:

• EDLRG, Spring 2023. Feb 2023 to May 2023. (EDLRG Website)

2024

2023

Best Paper Runner-Up Award

Oral

Oral

2022

2021

2018

Paddle-Lite is an updated version of Paddle-Mobile, an open-open source deep learning framework designed to make it easy to perform inference on mobile, embeded, and IoT devices. It is compatible with PaddlePaddle and pre-trained models from other sources, reported in NeurIPS Expo, Baidu Create, Wave Summit+.

• Workshop Chair:
  • Publicity Chair, International Workshop on Resource-Efficient Learning for Knowledge Discovery (RelKD 2023) @ KDD 2023

• Program Committee Member and Reviewer:
  • NeurIPS'22, 23
  • ICLR'24
  • ICML'22, 23, 24
  • CVPR'22, 23, 24
  • ICCV'23
  • ECCV'22
  • KDD'23
  • AAAI'22, 23, 24
  • IROS'23
  • TNNLS
  • SDM'24

• Teaching Assistant at Rutgers University

  • 14:332:351 - Programming Methodology II, Fall 2020
    Instructor: Prof. Saman Zonouz   

  • 14:332:351 - Programming Methodology II, Fall 2023
    Instructor: Prof. Yao Liu   

• Wenjin Zhang, Ph.D. at Rutgers University
  Topic: Quantization in Model Compression.

• Justin Ding, Master student at Rutgers University
  Topic: Pruning in Model Compression of "Graduate Special Problem"
  

• Linqi Xiao, Master student at Rutgers University
  Topic: Error Correct Coding of "Graduate Special Problem"
  

• Srinihar Bondalapati, Master student at Rutgers University
  Topic: Quantization in Model Compression
  

• Yue Wang, Master student at Rutgers University
  Topic: Dataset Distillation, Pruning in Model Compression of "Graduate Special Problem"
  

• Veena Vrushi, Undergraduate student at Rutgers University
  Topic: Deep Learning of "Project SUPER Research Program".
  

• Vijay Maddila, Graduate student at Rutgers University
  Topic: Large Language Models.
  

• Ayan Patel, High school student at High Technology High School
  Topic: Deep Learning.
  

• Zhiyu Chen, Master student at Rutgers University
  Topic: Large Language Models of "Graduate Special Problem".
  

• Efficient Diffusion Models and Large Language Models: Quantization, Pruning, and LoRA. (Video)
  July, 2023.
  

• Doctor of Philosophy (Ph.D.)
  • Best Paper Runner-Up Award at DCAA Workshop @ AAAI, 2023
  • First Place of Classification Track: Fair and Intelligent Embedded System Challenge in Tiny and Fair ML Design Competition @ ESWEEK 2023
  • Sixth Place of 2023 ACM/IEEE TinyML Design Contest at ICCAD
  • SGS Conference Travel and Research Award, 2023.

• Master of Science (M.E.)
  • Graduate Student Academic Scholarship, 2017, 2018

• Bachelor of Engineering (B.E.)
  • Postgraduate Recommendation (10% in EE at Jilin University), 2016
  • Outstanding Graduates, 2016
  • Second Prize Scholarship, 2014, 2015, 2016

In addition to my academic work, I am a fan of Basketball, Soccer, Formula 1, Snooker. I love Tracy McGrady, Stephen Curry, Lionel Messi, PIS (YaphetS).

I'm an experienced player of DOTA/DOTA2, World of Warcraft, Warcraft III, manipulating Druid (Balance Druid), DH (Havoc Demon Hunter) in WoW, and NE (Night Elf) in Warcraft III. I would like record some impressive moments:

• World top 10 DPS of Balance Druid with H4 (Flamebender Ka'graz) in Blackrock Foundry reported on WCL, World of Warcraft, 2015
  
• Raid Leader for defeating the Heroic Highmaul Raid in the Warlords of Draenor, World of Warcraft, 2014
  • I gathered my fourteen friends and together we conquered the Heroic Highmaul raid. It was an incredibly impressive experience that we won't soon forget.
• Member of DOTA school team (1/5) in Jilin City No.1 High School, DOTA, 2011
  
• Ladder Rank: 147, Hearthstone Legend, 2016
  
• Ladder Rank: 698, Witch Doctor, Season 9, Diablo III, 2016
  

I derive great pleasure from listening to the music that owns wonderful rhythm, especially R&B, and classical music from Chopin, Bach, Paganini.

Xiaolan (name is inspired from "Detective Conan"), my adorable grey and white cat with sparkling eyes, which appears in my NeurIPS'21 paper "CHIP", is playful, affectionate, and loves to cuddle. Say hi, Xiaolan!

*Last updated on 02/2024*
Inspired by Jon Barron