Ji Lin

PhD student, Massachusetts Institute of Technology

Joined

October 2017

Names

Ji Lin

Emails

****@gmail.com (Confirmed)

****@mails.tsinghua.edu.cn (Confirmed)

****@berkeley.edu (Confirmed)

****@mit.edu (Confirmed)

Personal Links

Homepage

Google Scholar

DBLP

Career & Education History

PhD student

Massachusetts Institute of Technology (mit.edu)

2019 – Present

Intern

OmniML (omniml.ai)

2021 – 2021

Intern

Adobe (adobe.com)

2020 – 2020

Undergrad student

Tsinghua University (tsinghua.edu.cn)

2014 – 2019

Advisors, Relations & Conflicts

PhD Advisor

Song Han

2019 – Present

Expertise

efficient deep learning

2017 – Present

Publications

VILA: On Pre-training for Visual Language Models
Ji Lin, Hongxu Yin, Wei Ping, Yao Lu, Pavlo Molchanov, Andrew Tao, Huizi Mao, Jan Kautz, Song Han
- OpenReview Archive Direct Upload
- Readers: Everyone
LIFT: Efficient Layer-wise Fine-tuning for Large Model Models
Ligeng Zhu, Lanxiang Hu, Ji Lin, Song Han
- Submitted to ICLR 2024
- Readers: Everyone
Smoothquant: Accurate and efficient post-training quantization for large language models
Ji Lin
- 28 Mar 2023
- OpenReview Archive Direct Upload
- Readers: Everyone
SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models
Guangxuan Xiao, Ji Lin, Mickael Seznec, Hao Wu, Julien Demouth, Song Han
- ICML 2023 Poster
- Readers: Everyone
Anycost GANs for Interactive Image Synthesis and Editing
Ji Lin, Richard Zhang, Frieder Ganz, Song Han, Jun-Yan Zhu
- 11 Oct 2022
- OpenReview Archive Direct Upload
- Readers: Everyone
On-Device Training Under 256KB Memory
Ji Lin, Ligeng Zhu, Wei-Ming Chen, Wei-Chen Wang, Chuang Gan, Song Han
- Published: 31 Oct 2022, Last Modified: 08 Feb 2026
- NeurIPS 2022 Accept
- Readers: Everyone
Efficient Spatially Sparse Inference for Conditional GANs and Diffusion Models
Muyang Li, Ji Lin, Chenlin Meng, Stefano Ermon, Song Han, Jun-Yan Zhu
- Published: 31 Oct 2022, Last Modified: 08 Feb 2026
- NeurIPS 2022 Accept
- Readers: Everyone
Network Augmentation for Tiny Deep Learning
Han Cai, Chuang Gan, Ji Lin, Song Han
- Published: 28 Jan 2022, Last Modified: 12 Oct 2025
- ICLR 2022 Poster
- Readers: Everyone
Memory-efficient Patch-based Inference for Tiny Deep Learning
Ji Lin, Wei-Ming Chen, Han Cai, Chuang Gan, Song Han
- Published: 09 Nov 2021, Last Modified: 31 Oct 2023
- NeurIPS 2021 Poster
- Readers: Everyone
HAQ: Hardware-Aware Automated Quantization With Mixed Precision.
Kuan Wang, Zhijian Liu, Yujun Lin, Ji Lin, Song Han
- 2019 (modified: 10 Nov 2022)
- CVPR2019
- Readers: Everyone

View all 15 publications

Co-Authors

View all 35 co-authors