Biography
Huanrui Yang (杨幻睿)
Postdoctoral Researcher
Department of Electrical Engineering and Computer Science
University of California, Berkeley
I'm actively recruiting self-motivated PhD students to join my group, including fast-track admission for Fall 2024 enrollment and regular admission for the 2025 Spring/Fall enrollment cycle. Potential research topics include AI efficiency, security, SW/HW codesign, and the application and optimization of AI-based systems in applications like autonomous driving, robotics, and natural/social science applications. If you are interested, please email me your research statement, CV, and transcripts with [PHD application] in the subject. Details can be found here
I am a Postdoctoral Scholar in the EECS department of UC Berkeley and Berkeley AI Research, under the supervision of Prof. Kurt Keutzer. My primary research aims to develop mathematical understandings of the efficiency and robustness of deep neural network models to make deep learning usable in real world tasks, with applications spanning from computer vision, generative model, and natural language processing. I am also broadly interested in deep learning privacy, interpretability, federated learning, and software-hardware co-design.
Before joining Berkeley I obtained my Ph.D. in Electrical and Computer Engineering from Duke University, under the supervision of Prof. Hai Li and Prof. Yiran Chen in the Duke CEI Lab in 2022. I earned my B.E. in Electronic Engineering from Tsinghua University in 2017.
News
I will join the Department of Electrical and Computer Engineering (ECE) at the University of Arizona (UA) as an assistant professor this August.
We are organizing the 3rd Workshop on Practical Deep Learning: Towards Efficient and Reliable LLMs at IEEE CAI 2024. Looking forward to your submissions and participation!
We are organizing the 1st Workshop on New Trends in AI-Generated Media and Security at AVSS 2024. We offer invite paper opportunities, please contact Prof. Shu Hu for details.
Our paper on effiicent feature modulation MoE is accepted at AAAI 2024.
Two papers (Q-Diffusion, QD-BEV) accepted at ICCV 2023. See you in Paris!
Educational background
PhD, Electrical and Computer Engineering, Duke University, 08/2017 to 05/2022
Dissertation: Towards Efficient and Robust Deep Neural Network Models
Advisor: Prof. Hai Li and Prof. Yiran Chen
BE, Electronic Engineering, Tsinghua University, 09/2013 to 07/2017
Diploma Thesis: On-chip Trainable Fully Connected Neural Network Accelerator Architecture (Outstanding Diploma Thesis of Tsinghua University, in Chinese)
Advisor: Prof. Yongpan Liu
High School, Experimental Class for Gifted Children, Beijing No.8 Middle School, 09/2009 to 06/2013
Professional experience
Postdoctoral Scholar, EECS/BAIR, University of California, Berkeley, 06/2022 to now
Advisor: Prof. Kurt Keutzer
Research Intern, NVIDIA Corporation, remote, 02/2021-09/2021
Supervised by Dr. Danny Yin, Dr. Pavlo Molchanov and Dr. Jan Kautz.
Research Intern, Microsoft Corporation, Redmond WA, 05/2018-08/2018
Supervised by Dr. Wenhan Wang and Dr. Yuxiong He
Awards
2021 WAIC Yunfan Award, Shanghai, 07/2021
2022 Duke ECE Outstanding Service Award, Duke University, 05/2022
CVPR 2023 Outstanding Reviewer Award, 06/2023
Outstanding Diploma Thesis, Tsinghua University, 06/2017
Academic Services
I have served as the reviewer for the following conferences and journals
NeurIPS, ICLR, ICML, MLSys, CVPR, ICCV, AAAI, IJCAI, KDD
IEEE TPAMI, IEEE TNNLS, TMLR, ACM TACO, ACM JETC, IEEE Access
Teaching Experience
Leading teaching assistant of ECE 590 / ECE 661 Computer Engineering Machine Learning and Deep Neural Nets (Fall 2019, Fall 2020 & Fall 2021), Duke University
Teaching assistant of ECE 681 Pattern Classification and Recognition (Spring 2019), Duke University
Teaching assistant of ECE 550D Fundamentals of Computer Systems and Engineering (Fall 2018), Duke University