Hi there
My name is Jiahao Li. I am currently a software engineer at ByteDance focusing on high performance model inference framework. Previously I received my bachelor degree from the Department of Computer Science and Technology, Tsinghua University. I am interested in cutting-edge AI algorithms and infrastructure, including CV/NLP/RL models and distributed training/inference system. It is awesome to make AI accessible to everyone!
Interests
- Computer Architecture
- Machine Learning
Education
B.Eng in Computer Science, 2017~2021
Tsinghua University
Experience
Work & Education
Software Engineer in Machine Learning System
ByteDance AML
R&D Intern in Computer Vision
ByteDance AILab
Researched and developed generative adversarial networks (GAN) for Toutiao, analyzed millions of training images, and significantly improved model performance
B.Eng in Compute Science
Tsinghua University
Learned internals of computer system and architecture, and implemented simple CPU, OS, Compiler, Router, Database, etc.
Publications
(2022).
Enabling In-situ Programmability in Network Data Plane: From Architecture to Language.
In Proceedings of the 19th USENIX Symposium on Networked Systems Design and Implementation (NSDI'22).
(2021).
In-situ Programmable Switching using rP4: Towards Runtime Data Plane Programmability.
In Proceedings of the Twentieth ACM Workshop on Hot Topics in Networks (HotNets'21).
(2021).
Separable Structure Modeling for Semi-supervised Video Object Segmentation.
In IEEE Transactions on Circuits and Systems for Video Technology (TCSVT).
(2020).
DSNet: A Flexible Detect-to-Summarize Network for Video Summarization.
In IEEE Transactions on Image Processing (TIP).
Contact
- liplus17@163.com
- Tsinghua University, Haidian District, Beijing 100084
- li-plus