Risultati della ricerca - Lin, Runqi

Time-Efficient Evaluation and Enhancement of Adversarial Robustness in Deep Neural Networks di Lin, Runqi

Testo

Eliminating Catastrophic Overfitting Via Abnormal Adversarial Examples Regularization di Lin, Runqi, Yu, Chaojian, Liu, Tongliang

Testo

On the Over-Memorization During Natural, Robust and Catastrophic Overfitting di Lin, Runqi, Yu, Chaojian, Han, Bo, Liu, Tongliang

Testo

Understanding and Enhancing the Transferability of Jailbreaking Attacks di Lin, Runqi, Han, Bo, Li, Fengwang, Liu, Tongling

Testo

Layer-Aware Analysis of Catastrophic Overfitting: Revealing the Pseudo-Robust Shortcut Dependency di Lin, Runqi, Yu, Chaojian, Han, Bo, Su, Hang, Liu, Tongliang

Testo

Instance-dependent Early Stopping di Yuan, Suqin, Lin, Runqi, Feng, Lei, Han, Bo, Liu, Tongliang

Testo

FORCE: Transferable Visual Jailbreaking Attacks via Feature Over-Reliance CorrEction di Lin, Runqi, Paren, Alasdair, Yuan, Suqin, Li, Muyang, Torr, Philip, Bibi, Adel, Liu, Tongliang

Testo

Mobile-VTON: High-Fidelity On-Device Virtual Try-On di Wan, Zhenchen, Chen, Ce, Lin, Runqi, Huang, Jiaxin, Chen, Tianxi, Xu, Yanwu, Liu, Tongliang, Gong, Mingming

Testo

PosA-VLA: Enhancing Action Generation via Pose-Conditioned Anchor Attention di Li, Ziwen, Wang, Xin, Zhang, Hanlue, Chen, Runnan, Lin, Runqi, He, Xiao, Huang, Han, Guo, Yandong, Karray, Fakhri, Liu, Tongliang, Gong, Mingming

Testo

Mirage2Matter: A Physically Grounded Gaussian World Model from Video di Gao, Zhengqing, Li, Ziwen, Wang, Xin, Huang, Jiaxin, Ren, Zhenyang, Shao, Mingkai, Zhang, Hanlue, Huang, Tianyu, Cheng, Yongkang, Guo, Yandong, Lin, Runqi, Wang, Yuanyuan, Liu, Tongliang, Zhang, Kun, Gong, Mingming

Testo