Alert button
Picture for Tianyu Pang

Tianyu Pang

Alert button

Test-Time Backdoor Attacks on Multimodal Large Language Models

Feb 13, 2024
Dong Lu, Tianyu Pang, Chao Du, Qian Liu, Xianjun Yang, Min Lin

Viaarxiv icon

Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast

Feb 13, 2024
Xiangming Gu, Xiaosen Zheng, Tianyu Pang, Chao Du, Qian Liu, Ye Wang, Jing Jiang, Min Lin

Viaarxiv icon

Weak-to-Strong Jailbreaking on Large Language Models

Feb 05, 2024
Xuandong Zhao, Xianjun Yang, Tianyu Pang, Chao Du, Lei Li, Yu-Xiang Wang, William Yang Wang

Viaarxiv icon

Benchmarking Large Multimodal Models against Common Corruptions

Jan 22, 2024
Jiawei Zhang, Tianyu Pang, Chao Du, Yi Ren, Bo Li, Min Lin

Viaarxiv icon

Temperature Balancing, Layer-wise Weight Analysis, and Neural Network Training

Dec 01, 2023
Yefan Zhou, Tianyu Pang, Keqin Liu, Charles H. Martin, Michael W. Mahoney, Yaoqing Yang

Viaarxiv icon

Finetuning Text-to-Image Diffusion Models for Fairness

Nov 11, 2023
Xudong Shen, Chao Du, Tianyu Pang, Min Lin, Yongkang Wong, Mohan Kankanhalli

Viaarxiv icon

Gaussian Mixture Solvers for Diffusion Models

Nov 02, 2023
Hanzhong Guo, Cheng Lu, Fan Bao, Tianyu Pang, Shuicheng Yan, Chao Du, Chongxuan Li

Viaarxiv icon

Intriguing Properties of Data Attribution on Diffusion Models

Nov 01, 2023
Xiaosen Zheng, Tianyu Pang, Chao Du, Jing Jiang, Min Lin

Viaarxiv icon

On Memorization in Diffusion Models

Oct 04, 2023
Xiangming Gu, Chao Du, Tianyu Pang, Chongxuan Li, Min Lin, Ye Wang

Figure 1 for On Memorization in Diffusion Models
Figure 2 for On Memorization in Diffusion Models
Figure 3 for On Memorization in Diffusion Models
Figure 4 for On Memorization in Diffusion Models
Viaarxiv icon