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

Oct 24, 2023	Grateful to be awarded the NeurIPS 2023 Scholar Award !
Oct 22, 2023	One preprint released To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Unsafe Images… For Now.
Sep 22, 2023	Two paper accepted by NeurIPS: Model Sparsity Can Simplify Machine Unlearning (Spotlight) and Selectivity Drives Productivity: Efficient Dataset Pruning for Enhanced Transfer Learning.
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.

selected publications

preprint

To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Unsafe Images... For Now

Yimeng Zhang*, Jinghan Jia*, Xin Chen, and 5 more authors

arXiv preprint arXiv:2310.11868 2023

Paper Code

@article{zhang2023generate,
  title = {To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Unsafe Images... For Now},
  author = {Zhang*, Yimeng and Jia*, Jinghan and Chen, Xin and Chen, Aochuan and Zhang, Yihua and Liu, Jiancheng and Ding, Ke and Liu, Sijia},
  journal = {arXiv preprint arXiv:2310.11868},
  year = {2023},
}

NeurIPS’23

Model sparsification can simplify machine unlearning

Jinghan Jia*, Jiancheng Liu*, Parikshit Ram, and 5 more authors

arXiv preprint arXiv:2304.04934 2023

Paper Code

@article{jia2023model,
  title = {Model sparsification can simplify machine unlearning},
  author = {Jia*, Jinghan and Liu*, Jiancheng and Ram, Parikshit and Yao, Yuguang and Liu, Gaowen and Liu, Yang and Sharma, Pranay and Liu, Sijia},
  journal = {arXiv preprint arXiv:2304.04934},
  year = {2023},
  publisher = {NeurIPS 2023},
}

SANER’23

CLAWSAT: Towards Both Robust and Accurate Code Models

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

2023

Paper Code Poster

  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},
  year = {2023},
  copyright = {Creative Commons Attribution 4.0 International}
}