Qi Zhou

3 papers Harbin Institute of Technology

• A Set of Generalized Components to Achieve Effective Poison-only Clean-label Backdoor Attacks with Collaborative Sample Selection and Triggers
• InfiFPO: Implicit Model Fusion via Preference Optimization in Large Language Models
• InfiGFusion: Graph-on-Logits Distillation via Efficient Gromov-Wasserstein for Model Fusion