Wang, Changsheng

3 publications

ICLR 2026 Downgrade to Upgrade: Optimizer Simplification Enhances Robustness in LLM Unlearning Yicheng Lang, Yihua Zhang, Chongyu Fan, Changsheng Wang, Jinghan Jia, Sijia Liu

ICML 2025 Invariance Makes LLM Unlearning Resilient Even to Unanticipated Downstream Fine-Tuning Changsheng Wang, Yihua Zhang, Jinghan Jia, Parikshit Ram, Dennis Wei, Yuguang Yao, Soumyadeep Pal, Nathalie Baracaldo, 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