Ji Lin

I am a research scientist at OpenAI, working on multimodal, reasoning, and synthetic data. I contributed to o3/o4-mini, GPT-4o, GPT-4.1, GPT-4.5, Operator, 4o imagegen, etc.

Previously, I completed my PhD at MIT EECS advised by Prof. Song Han. Before that, I received my B.Eng. in Electronic Engineering from Tsinghua University, and M.Sc. in EECS from MIT. I've interned/worked at Adobe Research, OmniML, and NVIDIA Research.

Publications [Full List]

* indicates equal contribution

VILA: On Pre-training for Visual Language Models Ji Lin*, Hongxu Yin*, Wei Ping, Yao Lu, Pavlo Molchanov, Andrew Tao, Huizi Mao, Jan Kautz, Mohammad Shoeybi, Song Han, CVPR 2024 / arXiv / Code

AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration Ji Lin*, Jiaming Tang*, Haotian Tang, Shang Yang, Xingyu Dang, Song Han, MLSys 2024 / arXiv / Code / TinyChat🔥 Integration: NVIDIA TRT-LLM / Intel Neural Compressor / vLLM / FastChat / HuggingFace TGI / LMDeploy / FriendliAI Best Paper Award

SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models Guangxuan Xiao*, Ji Lin*, Mickael Seznec, Julien Demouth, Song Han, ICML 2023 / arXiv / Code / Faster Transformer Integration / Intel Neural Compressor Integration

PockEngine: Sparse and Efficient Fine-tuning in a Pocket Ligeng Zhu, Lanxiang Hu, Ji Lin, Wei-Ming Chen, Wei-Chen Wang, Chuang Gan, Song Han, MICRO-56 / arXiv

Efficient Spatially Sparse Inference for Conditional GANs and Diffusion Models Muyang Li, Ji Lin, Chenlin Meng, Stefano Ermon, Song Han, Jun-Yan Zhu NeurIPS 2022 / arXiv / Project Page / Code / Video

On-Device Training Under 256KB Memory Ji Lin*, Ligeng Zhu*, Wei-Ming Chen, Wei-Chen Wang, Chuang Gan, Song Han NeurIPS 2022 / arXiv / Project Page Press: MIT News (homepage spotlight)

Network Augmentation for Tiny Deep Learning Han Cai, Chuang Gan, Ji Lin, Song Han NeurIPS 2021 / arXiv / Code

MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning Ji Lin, Wei-Ming Chen, Han Cai, Chuang Gan, Song Han NeurIPS 2021 / arXiv / Project Page Press: MIT News / TechTalks / TheNextWeb / AIM / TechMonitor

Anycost GANs for Interactive Image Synthesis and Editing Ji Lin, Richard Zhang, Frieder Ganz, Song Han, Jun-Yan Zhu CVPR 2021 / arXiv / Project Page / Code / Video / Demo Video / Colab Tutorial

MCUNet: Tiny Deep Learning on IoT Devices Ji Lin, Wei-Ming Chen, Yujun Lin, John Cohn, Chuang Gan, Song Han NeurIPS 2020 / arXiv / Project Page / Code / Demo Video Press: MIT News (homepage spotlight) / WIRED / MIT TR-China / IBM / Morning Brew / Stacey on IoT / Analytics Insight / Techable / Tendencias

Differentiable Augmentation for Data-Efficient GAN Training Shengyu Zhao, Zhijian Liu, Ji Lin, Jun-Yan Zhu, Song Han NeurIPS 2020 / arXiv / Project Page / Code / Slides / Colab Tutorial Press: VentureBeat

GAN Compression: Efficient Architectures for Interactive Conditional GANs Muyang Li, Ji Lin, Yaoyao Ding, Zhijian Liu, Jun-Yan Zhu, Song Han CVPR 2020 / arXiv / Project Page / Code / Video / Demo Video / Slides

APQ: Joint Search for Network Architecture, Pruning and Quantization Policy Tianzhe Wang, Kuan Wang, Han Cai, Ji Lin, Zhijian Liu, Hanrui Wang, Yujun Lin, Song Han CVPR 2020 / arXiv

AutoML for Architecting Efficient and Specialized Neural Networks Han Cai*, Ji Lin*, Yujun Lin*, Zhijian Liu*, Kuan Wang*, Tianzhe Wang*, Ligeng Zhu*, Song Han IEEE Micro

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 NeurIPS 2019 Workshop / arXiv Project Page / Demo / Code Press: MIT News / MIT Technology Review / WIRED / Engadget/ NVIDIA News / Industry Integration@NVIDIA

HAQ: Hardware-Aware Automated Quantization Kuan Wang*, Zhijian Liu*, Yujun Lin*, Ji Lin, Song Han CVPR 2019 / arXiv Hardware-Centric AutoML for Mixed-Precision Quantization Kuan Wang*, Zhijian Liu*, Yujun Lin*, Ji Lin, Song Han IJCV Project Page / Code

AMC: AutoML for Model Compression and Acceleration on Mobile Devices Yihui He*, Ji Lin*, Zhijian Liu, Hanrui Wang, Li-Jia Li, Song Han ECCV 2018 / arXiv / Project Page / Poster / Code

Runtime Neural Pruning Ji Lin*, Yongming Rao*, Jiwen Lu, Jie Zhou NIPS 2017 Runtime Network Routing for Efficient Image Classification Yongming Rao, Jiwen Lu, Ji Lin, Jie Zhou T-PAMI