Career Profile
I am Junguang Jiang. I graduated from Tsinghua University under the supervision of Mingsheng Long. Now, I work as a machine learning engineer in the display advertising team at Alimama.
I created a Transfer Learning Library TLlib and got over .
Here is my Chinese resume (中文简历) and English resume.
Publications
ForkMerge: Overcoming Negative Transfer in Multi-Task Learning
Conference and Workshop on Neural Information Processing Systems (NIPS), 2023
[Paper]
Debiased Pseudo Labeling in Self-Training
Conference and Workshop on Neural Information Processing Systems (NIPS Oral), 2022
Decoupled Adaptation for Cross-Domain Object Detection
The Tenth International Conference on Learning Representations (ICLR), 2022
Regressive Domain Adaptation for Unsupervised Keypoint Detection
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021
Resource Efficient Domain Adaptation
ACM Annual Conference on Multimedia (ACMMM), 2020 (Oral)
[Paper]
Projects
Open Source Libraries -- TLlib
- An open-source and well-documented library for Transfer Learning, Domain Adaptation, Task Adaptation, and Domain Generalization.
- First Author and contribute more than 20k lines of code.
Selected Course Projects -- TinyCCompiler
- A tiny C compiler based on LLVM and ANTLR4.
- Project for Compiler Principles which is scored A+.
- First Author and responsible for implementing symbol tables, error handling, functions, arrays, pointers, etc.
Experiences
- Research on multi-task learning, mainly for recommendation tasks
Teaching Assistant for Machine Learning, Fall 2021
- Research on transfer learning for both 3D and 2D keypoint detection, which is then applied to the Augmented Reality (AR) applications.
- Propose regressive domain adaptation methods for unsupervised keypoint detection to decrease the labeling cost for 3D and 2D keypoints of hand gestures.
- Related work is published at CVPR2020.
Education & Awards
- Advised by Mingsheng Long
- Comprehensive Excellence Award (Huawei Scholarship, top 5%), Tsinghua University, 2021
- GPA 3.9 Ranking 2nd/83
- National Scholarship (top 1%), Tsinghua University, 2019
- Comprehensive Excellence Award (Huawei Scholarship, top 1%), Tsinghua University, 2018