Chengcan Wu

According to our database, Chengcan Wu authored at least 3 papers in 2025.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2025

Reliable Unlearning Harmful Information in LLMs with Metamorphosis Representation Projection.

Chengcan Wu, Zeming Wei, Huanran Chen, Yinpeng Dong, Meng Sun

CoRR, August, 2025

ReGA: Representation-Guided Abstraction for Model-based Safeguarding of LLMs.

Zeming Wei, Chengcan Wu, Meng Sun

CoRR, June, 2025

Mitigating Fine-tuning Risks in LLMs via Safety-Aware Probing Optimization.

Chengcan Wu, Zhixin Zhang, Zeming Wei, Yihao Zhang, Meng Sun

CoRR, May, 2025