Skip to content
View ljcc0930's full-sized avatar

Highlights

  • Pro

Organizations

@thucg

Block or report ljcc0930

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
ljcc0930/README.md

Hi there 👋

My name is Jiancheng (JC) Liu. I am a graduate student in Computer Science and Engineering at Michigan State University. I currently work at OPTML Group, advised by Prof. Sijia Liu. My research goal is to foster a seamless integration of AI with humanity, through a deeper comprehension of natural laws and societal dynamics. A recent topic of my research is enhancing AI's trustworthiness through Machine Unlearning.

I received my B.E. in computer science from the Institute for Interdisciplinary Information Sciences (Yao Class, headed by Prof. Andrew Chi-Chih Yao), Tsinghua University. I am fortunate to have been advised by Prof. Shi-Min Hu on my undergraduate research and bachelor thesis. In 2018, I had some wonderful times working with Prof. Wojciech Matusik and Dr. Yuanming Hu at MIT.

Before studying at MSU, I joined Taichi Graphics Technology, Inc. as a start-up member in 2021. During my employment, I focused on developing Taichi Lang and delving into differentiable physics.


Email: liujia45 (at) msu (dot) edu [CV] [Google Scholar] [GitHub]

My publications by category

Paper Title Venue
Repository
Unlearning for LLMs
Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning NeurIPS'24 SafeGenAI OPTML-Group/Unlearn-Simple
WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Models NeurIPS'24 OPTML-Group/WAGLE
SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearning EMNLP'24 OPTML-Group/Unlearn-WorstCase
Unlearning for Diffusion Models
Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models NeurIPS'24 OPTML-Group/AdvUnlearn
UnlearnCanvas: A Stylized Image Dataset to Benchmark Machine Unlearning for Diffusion Models NeurIPS'24 D&B OPTML-Group/UnlearnCanvas
To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Unsafe Images... For Now ECCV'24 OPTML-Group/Diffusion-MU-Attack
SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation ICLR'24 (Spotlight) OPTML-Group/Unlearn-Saliency
Unlearning for Classification Models
Forget Vectors at Play: Universal Input Perturbations Driving Machine Unlearning in Image Classification In Submission OPTML-Group/Changchangsun/Forget-Vector
Challenging Forgets: Unveiling the Worst-Case Forget Sets in Machine Unlearning ECCV'24 OPTML-Group/Unlearn-WorstCase
Model Sparsity Can Simplify Machine Unlearning NeurIPS'23 (Spotlight) OPTML-Group/Unlearn-Sparse
Physical-informed ML
Towards Universal Mesh Movement Networks NeurIPS'24 (Spotlight) mesh-adaptation/UM2N
Complex Locomotion Skill Learning via Differentiable Physics Technical Report erizmr/Complex-locomotion-skill-learning-via-differentiable-physics
ChainQueen: A Real-Time Differentiable Physical Simulator for Soft Robotics ICRA'19 yuanming-hu/ChainQueen

Pinned Loading

  1. OPTML-Group/Unlearn-Saliency OPTML-Group/Unlearn-Saliency Public

    [ICLR24 (Spotlight)] "SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation" by Chongyu Fan*, Jiancheng Liu*, Yihua Zhang, Eric Wong, D…

    Python 110 19

  2. OPTML-Group/Unlearn-Sparse OPTML-Group/Unlearn-Sparse Public

    [NeurIPS23 (Spotlight)] "Model Sparsity Can Simplify Machine Unlearning" by Jinghan Jia*, Jiancheng Liu*, Parikshit Ram, Yuguang Yao, Gaowen Liu, Yang Liu, Pranay Sharma, Sijia Liu

    Python 65 7

  3. OPTML-Group/Unlearn-WorstCase OPTML-Group/Unlearn-WorstCase Public

    [ECCV24] "Challenging Forgets: Unveiling the Worst-Case Forget Sets in Machine Unlearning" by Chongyu Fan*, Jiancheng Liu*, Alfred Hero, Sijia Liu

    Python 19 1

  4. OPTML-Group/Unlearn-Simple OPTML-Group/Unlearn-Simple Public

    "Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning" by Chongyu Fan*, Jiancheng Liu*, Licong Lin*, Jinghan Jia, Ruiqi Zhang, Song Mei, Sijia Liu

    Python 20 6

  5. erizmr/Complex-locomotion-skill-learning-via-differentiable-physics erizmr/Complex-locomotion-skill-learning-via-differentiable-physics Public

    Python 3 1