Jinghan Jia

Room 3210

428 S Shaw LN

East Lansing, MI, USA

I am Jinghan Jia, a scecond year Ph.D. student from OPTML Group at Michigan State University, supervised by Prof. Sijia Liu. My research focuses on the truthworthy and scalable ML algorithms. In general, my research spans the areas of machine learning (ML)/ deep learning (DL), optimization theory, computer vision, code understanding, natural language processing, and security. These research topics provide a solid background for my current and future research: Making AI system safe and scalable.

news

Jan 15, 2023	One paper accepted by CVPR: Text-Visual Prompting for Efficient 2D Temporal Video Grounding.
Jan 15, 2023	One paper accepted by ICLR: TextGrad: Advancing Robustness Evaluation in NLP by Gradient-Driven Optimization.
Dec 16, 2022	One paper accepted by SANER: CLAWSAT: Towards Both Robust and Accurate Code Models; Equally contributed by Jinghan Jia (MSU) and Shashank Srikant (MIT).
Nov 12, 2022	One paper accepted by SLOWDNN.
Sep 20, 2022	One paper accepted by TSRML.

selected publications

CLAWSAT: Towards Both Robust and Accurate Code Models

Jinghan Jia, Shashank Srikant, Tamara Mitrovska, and 4 more authors

2022

Bib HTML Code

  doi = {10.48550/ARXIV.2211.11711},
  author = {Jia, Jinghan and Srikant, Shashank and Mitrovska, Tamara and Gan, Chuang and Chang, Shiyu and Liu, Sijia and O'Reilly, Una-May},
  keywords = {Machine Learning (cs.LG), Programming Languages (cs.PL), Software Engineering (cs.SE), FOS: Computer and information sciences, FOS: Computer and information sciences},
  title = {CLAWSAT: Towards Both Robust and Accurate Code Models},
  publisher = {arXiv},
  year = {2022},
  copyright = {Creative Commons Attribution 4.0 International}
}