Guojun Ma

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

SAFER: Probing Safety in Reward Models with Sparse Autoencoder

AnyEdit: Edit Any Knowledge Encoded in Language Models

Grounding Language with Vision: A Conditional Mutual Information Calibrated Decoding Strategy for Reducing Hallucinations in LVLMs

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