jilin.eecs AT gmail
I am a research scientist at OpenAI.
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.
* indicates equal contribution
VILA: On Pre-training for Visual Language Models
|
AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration
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
|
PockEngine: Sparse and Efficient Fine-tuning in a Pocket
|
Efficient Spatially Sparse Inference for Conditional GANs and Diffusion Models
|
On-Device Training Under 256KB Memory
Press:
MIT News (homepage spotlight)
|
Network Augmentation for Tiny Deep Learning
|
MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning
|
Anycost GANs for Interactive Image Synthesis and Editing
|
MCUNet: Tiny Deep Learning on IoT Devices
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
Press:
VentureBeat
|
GAN Compression: Efficient Architectures for Interactive Conditional GANs
|
APQ: Joint Search for Network Architecture, Pruning and Quantization Policy
|
AutoML for Architecting Efficient and Specialized Neural Networks
|
TSM: Temporal Shift Module for Efficient Video Understanding
ICCV 2019 /
arXiv
Training Kinetics in 15 Minutes: Large-scale Distributed Training on Videos
Press:
MIT News /
MIT Technology Review /
WIRED /
Engadget/
NVIDIA News /
Industry Integration@NVIDIA
|
HAQ: Hardware-Aware Automated Quantization
Hardware-Centric AutoML for Mixed-Precision Quantization
|
AMC: AutoML for Model Compression and Acceleration on Mobile Devices
|
Runtime Neural Pruning
Runtime Network Routing for Efficient Image Classification
|