Fan, Chongyu

8 publications

NeurIPS 2025 Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning Chongyu Fan, Jiancheng Liu, Licong Lin, Jinghan Jia, Ruiqi Zhang, Song Mei, Sijia Liu

NeurIPS 2025 The Fragile Truth of Saliency: Improving LLM Input Attribution via Attention Bias Optimization Yihua Zhang, Changsheng Wang, Yiwei Chen, Chongyu Fan, Jinghan Jia, Sijia Liu

ICML 2025 Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond Chongyu Fan, Jinghan Jia, Yihua Zhang, Anil Ramakrishna, Mingyi Hong, Sijia Liu

ECCV 2024 Challenging Forgets: Unveiling the Worst-Case Forget Sets in Machine Unlearning Chongyu Fan, Jiancheng Liu, Alfred Hero, Sijia Liu

NeurIPS 2024 Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models Yimeng Zhang, Xin Chen, Jinghan Jia, Yihua Zhang, Chongyu Fan, Jiancheng Liu, Mingyi Hong, Ke Ding, Sijia Liu

ICLR 2024 SalUn: Empowering Machine Unlearning via Gradient-Based Weight Saliency in Both Image Classification and Generation Chongyu Fan, Jiancheng Liu, Yihua Zhang, Eric Wong, Dennis Wei, Sijia Liu

NeurIPSW 2024 Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning Chongyu Fan, Jiancheng Liu, Licong Lin, Jinghan Jia, Ruiqi Zhang, Song Mei, Sijia Liu

NeurIPS 2024 UnlearnCanvas: Stylized Image Dataset for Enhanced Machine Unlearning Evaluation in Diffusion Models Yihua Zhang, Chongyu Fan, Yimeng Zhang, Yuguang Yao, Jinghan Jia, Jiancheng Liu, Gaoyuan Zhang, Gaowen Liu, Ramana Kompella, Xiaoming Liu, Sijia Liu