Ji Lin

         


Contact:

jilin AT mit.edu

About Me

I am currently a first-year Ph.D. student at MIT EECS. Previously, I graduated from Department of Electronic Engineering, Tsinghua University.

My research interests lie in efficient and hardware-friendly machine learning and its applications.

Education

Massachusetts Institute of Technology , USA
Ph.D. student in EECS • Aug. 2019 - Now

Tsinghua University , China
B.Eng. in Electronic Engineering • Aug. 2014 - June 2019

Selected Publications

* indicates equal contribution

TSM: Temporal Shift Module for Efficient Video Understanding
Ji Lin, Chuang Gan, Song Han
ICCV 2019 / arXiv
Training Kinetics in 15 Minutes: Large-scale Distributed Training on Videos
Ji Lin, Chuang Gan, Song Han
HAQ: Hardware-Aware Automated Quantization
Kuan Wang*, Zhijian Liu*, Yujun Lin*, Ji Lin, Song Han
Oral Presentation
Defensive Quantization: When Efficiency Meets Robustness
Ji Lin, Chuang Gan, Song Han
ICLR 2019 / arXiv / MIT News
AMC: AutoML for Model Compression and Acceleration on Mobile Devices
Adaptive Mixture of Low-Rank Factorizations for Compact Neural Modeling
Runtime Network Routing for Efficient Image Classification
Runtime Neural Pruning
Learning Discriminative Aggregation Network for Video-based Face Recognition
Spotlight Presentation
Consistent-aware Deep Learning for Person Re-identification in a Camera Network
Spotlight Presentation

Academic Service

  • Invited reviewer for ICML, NeurIPS, CVPR, ICCV, IJCAI, AAAI, ACMMM

Honors and Awards

Honors

  • Outstanding Thesis Award, Outstanding Graduate, Tsinghua University • 2019
  • China National Scholarship, Ministry of Education of P.R. China • 2017
  • Cai Xiong Scholarship (10/3300), Tsinghua University • 2018
  • Spark Scientific and Technological Innovation Program (50/3300), Tsinghua University • 2017-2018

Challenges

  • 1st Prize of Visual Wakeup Words (VWW) Challenge • 2019
  • 3rd Prize of IEEE 2019 Low Power Image Recognition Challenge (LPIRC’19) • 2019
  • 3rd Prize of IEEE 2016 Low Power Image Recognition Challenge (LPIRC’16) • 2016