Haotian Tang

Haotian Tang is a fourth-year Ph.D. student at HAN LAB of MIT EECS, advised by Prof. Song Han. His research interest is systems and machine learning (SysML). For his Ph.D. study, he works with labmates on designing efficient 3D deep learning primitives (PVConv, NeurIPS’19 spotlight), networks (SPVNAS, ECCV’20 and TPAMI’21), inference libraries (TorchSparse, MLSys’22) and specialized accelerators (PointAcc, MICRO’21). They then apply them in real-world auto-driving applications (BEVFusion, ICRA’23).

He received an M.Sc. in EECS at MIT in 2022. Before that, he graduated with highest honor from the department of Computer Science and Engineering at Shanghai Jiao Tong University in 2020, where he was fortunately advised by Prof. Hongtao Lu. He was also affiliated with the IEEE Honor Class at SJTU.
Avatar photo

Posts by Haotian Tang

Decorative image of VILA and Jetson Orin workflow.
Generative AI / LLMs

Visual Language Intelligence and Edge AI 2.0

VILA is a family of high-performance vision language models developed by NVIDIA Research and MIT. The largest model comes with ~40B parameters and the smallest... 8 MIN READ