Pengfei Li

I am Pengfei Li, a third-year CS Ph.D. student in University of California, Riverside, under the supervision of Prof. Shaolei Ren. I obtained a M.S.E degree in Laboratory for Computational Sensing and Robotics (LCSR), Johns Hopkins University, under the supervision of Prof. Alan Yuille and Prof. Gregory Hager.

Prior to joining JHU, I graduated from Zhejiang University with honors, majoring in Electrical Engineering. I was also a member of Advanced Class of Engineering Education (ACEE) in Chu Kochen Honor College (CKC). In summer 2017, I took part in the International Summer Research Program in UCSD under the supervision of Prof. Atanasov as a research intern.

Email / Twitter / Github / CV / Google Scholar

profile photo

  • One paper accepted by ICML 2023, see you all in Hawaii !🥳
  • Received Student Travel Grant from INFOCOM 2022.
  • One paper accepted to INFOCOM 2022.

Highlighted Research

My research interests mainly focus on Nonlinear Optimization, Machine Learning and Graph Theory. Representative papers are highlighted, * indicates equal contributions.

Learning for Edge-Weighted Online Bipartite Matching with Robustness Guarantees
Pengfei Li, Jianyi Yang, Shaolei Ren
ICML, 2023
paper avaliable soon

A novel RL-based approach for edge-weighted online bipartite matching with robustness guarantees, achieving both good average-case performance and strict worst-case guarantee. This framework (LOMAR) supports training the RL policy by explicitly considering the online robustification operation.

Making AI Less "Thirsty": Uncovering and Addressing the Secret Water Footprint of AI Models
Pengfei Li, Jianyi Yang, Mohammad A. Islam, Shaolei Ren
code / arXiv / Media

The growing carbon footprint of large artificial intelligence (AI) models, such as GPT-3, has been undergoing public scrutiny. Unfortunately, however, the equally important and enormous water footprint of AI models has remained under the radar. We highlight the necessity of holistically addressing water footprint along with carbon footprint to enable truly sustainable AI.

Expert-Robustified Learning for Online Optimization with Memory Cost.
Pengfei Li, Jianyi Yang, Shaolei Ren

We propose a novel expert-robustified learning (ERL) approach, with a novel projection operator. Our method can be easily extended to multistep memory costs, achieving both good average performance and strict robustness.

Expert-Calibrated Learning for Online Optimization with Switching Costs
Pengfei Li*, Jianyi Yang*, Shaolei Ren
paper / arxiv / video / slides

EC-L2O is the first to address the "how to learn" challenge for online convex optimization, which requires new algorithm design, closed-form differentiation and theoritical analysis.

Multi-person 3D Pose Estimation in Crowded Scenes Based on Multi-View Geometry
He Chen*, Pengfei Guo*, Pengfei Li, Gim Hee Lee, Gregory Chirikjian
ECCV, spotlight, 2020
paper / video / code

A novel 3D crowd human pose estimation method, which proposed a faster cross-view matching based on graphical model

Sparse Activation Maps for Interpreting 3D Object Detection
Qiuxiao Chen, Pengfei Li, Meng Xu, Xiaojun Qi.
Safe Artificial Intelligence for Automated Driving(CVPRW), Best Paper Finalist, 2021
paper / video

A technique to interpret 3D object detection results from volumetric-based networks

Archived projects
Car Pose Estimation with Context Constraints
Pengfei Li*, Weichao Qiu*, Michael Peven*, Gregory D. Hager, Alan L. Yuille
paper/ video

Estimated car pose and activity based on global information (ground plane parameter) estimation. Copy real car's behavior into a game engine, UE4.

Feature Extracted DOA Estimation Algorithm Using Acoustic Array for Drone Surveillance
Xianyu Chang, Chaoqun Yang, Xiufang Shi, Pengfei Li, Zhiguo Shi, Jiming Chen
VTC-Fall, 2018

Reviewer for IEEE Systems Journal
IEEE Student Member
IEEE ComSoc Student Member
ACM Student Member
cs188 Graduate Student Instructor, CS010B Fall 2021
Graduate Student Instructor, CS010B Winter 2021
Graduate Student Instructor, CS010B Spring 2021

Visitors from the world

Template from Jon Barron,