Yuan, Shengming

4 publications

NeurIPS 2025 FlexAC: Towards Flexible Control of Associative Reasoning in Multimodal Large Language Models Shengming Yuan, Xinyu Lyu, Shuailong Wang, Beitao Chen, Jingkuan Song, Lianli Gao

NeurIPS 2025 SafePTR: Token-Level Jailbreak Defense in Multimodal LLMs via Prune-Then-Restore Mechanism Beitao Chen, Xinyu Lyu, Shengming Yuan, Jingkuan Song, Heng Tao Shen, Lianli Gao

ECCV 2024 Any Target Can Be Offense: Adversarial Example Generation via Generalized Latent Infection Youheng Sun, Shengming Yuan, Xuanhan Wang, Lianli Gao, Jingkuan Song

NeurIPS 2022 Natural Color Fool: Towards Boosting Black-Box Unrestricted Attacks Shengming Yuan, Qilong Zhang, Lianli Gao, Yaya Cheng, Jingkuan Song