1 code implementation • 13 Feb 2024 • Xiangming Gu, Xiaosen Zheng, Tianyu Pang, Chao Du, Qian Liu, Ye Wang, Jing Jiang, Min Lin
A multimodal large language model (MLLM) agent can receive instructions, capture images, retrieve histories from memory, and decide which tools to use.
1 code implementation • 1 Nov 2023 • Xiaosen Zheng, Tianyu Pang, Chao Du, Jing Jiang, Min Lin
Data attribution seeks to trace model outputs back to training data.
1 code implementation • ACL 2022 • Xiaosen Zheng, Jing Jiang
We empirically show that our memorization attribution method is faithful, and share our interesting finding that the top-memorized parts of a training instance tend to be features negatively correlated with the class label.