Welcome to Shang Yang’s Home!

 

Hi! I am Shang Yang, a first-year Ph.D. student at HAN LAB of MIT EECS, advised by Prof. Song Han. Before that, I received my Bachelor degree with highest honor from the Department of Electronic Engineering, Tsinghua University, China, where I was fortunate to be advised by Prof. Yu Wang.

My long-term goal is to build efficient machine learning systems for applications/workloads at different scales, such as Point Clouds and LLMs. Recently, I am activately working on the quantization of LLMs.

Please check my CV here!

   

Selected Publications

TorchSparse++: Efficient Training and Inference Framework for Sparse Convolution on GPUs
Haotian Tang*, Shang Yang*, Zhijian Liu, Ke Hong, Zhongming Yu, Xiuyu Li, Guohao Dai, Yu Wang, Song Han.
Accepted by MICRO, 2023.

Heuristic Adaptability to Input Dynamics for SpMM on GPUs
Guohao Dai, Guyue Huang, Shang Yang, Zhongming Yu, Hengrui Zhang, Yufei Ding, Yuan Xie, Huazhong Yang, Yu Wang.
Accepted by DAC, 2022. Best Paper Award Nominee (Top 6 in all 223 accepted papers).

   

Preprints

AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration
Ji Lin*, Jiaming Tang*, Haotian Tang, Shang Yang, Xinyu Dang, Song Han.

   

Education

MITMIT                                 Since 09/2023
 Ph.D. Student at MIT EECS
 Advised by Prof. Song Han

tsinghuaTsinghua University                08/2019 - 07/2023
 Overall GPA: 3.99/4.0, Rank: 1/256
 B.Eng. in Electronic Information Science and Technology

   

Research Experiences

MITMIT                            07/2022 - 08/2023
 Research Intern at HAN Lab, advised by Prof. Song Han

tsinghuaTsinghua University               10/2020 - 07/2023
 Undergraduate at NICS-EFC, advised by Prof. Yu Wang