Houcheng Jiang

SPEED: Scalable, Precise, and Efficient Concept Erasure for Diffusion Models

DualEdit: Mitigating Safety Fallback in LLM Backdoor Editing via Affirmation-Refusal Regulation

Goal-Aware Identification and Rectification of Misinformation in Multi-Agent Systems

Contrastive Weak-to-Strong Generalization

AnyEdit: Edit Any Knowledge Encoded in Language Models

AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models

Reinforced Lifelong Editing for Language Models

SPEED: Scalable, Precise, and Efficient Concept Erasure for Diffusion Models

Neuron-Level Sequential Editing for Large Language Models