Publications

( “*” indicates equal contribution.)

Conferences

Can Adversarial Examples Be Parsed to Reveal Victim Model Information?
WACV 2025
Jiancheng Liu*, Yuguang Yao*, Yifan Gong*, Xiaoming Liu, Yanzhi Wang, Xue Lin, Sijia Liu
Towards Universal Mesh Movement Networks
NeurIPS 2024 (Spotlight)
Mingrui Zhang, Chunyang Wang, Stephan C. Kramer, Joseph G. Wallwork, Siyi Li, Jiancheng Liu, Xiang Chen, Matthew D. Piggott
WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Models
NeurIPS 2024
Jinghan Jia, Jiancheng Liu, Yihua Zhang, Parikshit Ram, Nathalie Baracaldo, Sijia Liu
Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models
NeurIPS 2024
Yimeng Zhang, Xin Chen, Jinghan Jia, Yihua Zhang, Chongyu Fan, Jiancheng Liu, Mingyi Hong, Ke Ding, Sijia Liu
UnlearnCanvas: A Stylized Image Dataset to Benchmark Machine Unlearning for Diffusion Models
NeurIPS 2024 Datasets and Benchmarks
Yihua Zhang, Chongyu Fan, Yimeng Zhang, Yuguang Yao, Jinghan Jia, Jiancheng Liu, Gaoyuan Zhang, Gaowen Liu, Ramana Rao Kompella, Xiaoming Liu, Sijia Liu
SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearning
EMNLP 2024
Jinghan Jia, Yihua Zhang, Yimeng Zhang, Jiancheng Liu, Bharat Runwal, James Diffenderfer, Bhavya Kailkhura, Sijia Liu
Challenging Forgets: Unveiling the Worst-Case Forget Sets in Machine Unlearning
ECCV 2024
Jiancheng Liu*, Chongyu Fan*, Alfred Hero, Sijia Liu
To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Unsafe Images... For Now
ECCV 2024
Yimeng Zhang*, Jinghan Jia*, Xin Chen, Aochuan Chen, Yihua Zhang, Jiancheng Liu, Ke Ding, Sijia Liu
SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation
ICLR 2024 (Spotlight)
Jiancheng Liu*, Chongyu Fan*, Yihua Zhang, Eric Wong, Dennis Wei, Sijia Liu
DeepZero: Scaling up Zeroth-Order Optimization for Deep Model Training
ICLR 2024
Aochuan Chen*, Yimeng Zhang*, Jinghan Jia, James Diffenderfer, Jiancheng Liu, Konstantinos Parasyris, Yihua Zhang, Zheng Zhang, Bhavya Kailkhura, Sijia Liu
Model Sparsity Can Simplify Machine Unlearning
NeurIPS 2023 (Spotlight)
Jiancheng Liu*, Jinghan Jia*, Parikshit Ram, Yuguang Yao, Gaowen Liu, Yang Liu, Pranay Sharma, Sijia Liu
Selectivity Drives Productivity: Efficient Dataset Pruning for Enhanced Transfer Learning
NeurIPS 2023
Yihua Zhang*, Yimeng Zhang*, Aochuan Chen*, Jinghan Jia, Jiancheng Liu, Gaowen Liu, Mingyi Hong, Shiyu Chang, Sijia Liu
ChainQueen: A Real-Time Differentiable Physical Simulator for Soft Robotics
ICRA 2019
Yuanming Hu, Jiancheng Liu*, Andrew Spielberg*, Joshua B. Tenenbaum, William T. Freeman, Jiajun Wu, Daniela Rus, Wojciech Matusik
Delving Deep Into Coarse-to-Fine Framework for Facial Landmark Localization
CVPR 2017 Workshop
Xi Chen, Erjin Zhou, Yuchen Mo, Jiancheng Liu, Zhimin Cao

Journals

Reverse Engineering of Deceptions on Machine- and Human-Centric Attacks
FnT 2024
Yuguang Yao, Xiao Guo, Vishal Asnani, Yifan Gong, Jiancheng Liu, Xue Lin, Xiaoming Liu, Sijia Liu
Deep Portrait Image Completion and Extrapolation
TIP 2020
Xian Wu, Rui-Long Li, Fang-Lue Zhang, Jian-Cheng Liu, Jue Wang, Ariel Shamir, Shi-Min Hu

Preprints

Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning
arXiv 2024, NeurIPS 2024 SafeGenAI Workshop
Jiancheng Liu*, Chongyu Fan*, Licong Lin*, Jinghan Jia, Ruiqi Zhang, Song Mei, Sijia Liu
Complex Locomotion Skill Learning via Differentiable Physics
arXiv 2022
Jiancheng Liu*, Yu Fang*, Mingrui Zhang*, Jiasheng Zhang, Yidong Ma, Minchen Li, Yuanming Hu, Chenfanfu Jiang, Tiantian Liu

Talks

Dynamic SNodes: Flexible Run-time Creation and Deletion of Taichi Fields
Taichi Developer Conference (TaichiCon) 02, September 2021
Presenter: Jiancheng Liu
Taichi Programming Language and Differentiable Physical Simulation
USTC Summer School - Advances in Computer Graphics, July 2021
Presenter: Ye Kuang, Jiancheng Liu