He, Zhenghao

3 publications

ICLR 2026 Toward Faithful Retrieval-Augmented Generation with Sparse Autoencoders Guangzhi Xiong, Zhenghao He, Bohan Liu, Sanchit Sinha, Aidong Zhang

ICCV 2025 GCAV: A Global Concept Activation Vector Framework for Cross-Layer Consistency in Interpretability Zhenghao He, Sanchit Sinha, Guangzhi Xiong, Aidong Zhang

MLJ 2025 MUSO: Achieving Exact Machine Unlearning in Over-Parameterized Regimes Ruikai Yang, Mingzhen He, Zhenghao He, Youmei Qiu, Xiaolin Huang