no code implementations • 3 Apr 2024 • Fengyuan Liu, Haochen Luo, Yiming Li, Philip Torr, Jindong Gu
In this work, we study the origin attribution of generated images in a practical setting where only a few images generated by a source model are available and the source model cannot be accessed.
1 code implementation • 14 Mar 2024 • Haochen Luo, Jindong Gu, Fengyuan Liu, Philip Torr
Given that VLMs rely on prompts to adapt to different tasks, an intriguing question emerges: Can a single adversarial image mislead all predictions of VLMs when a thousand different prompts are given?
1 code implementation • 30 May 2023 • Haochen Luo, Yi Zhou, Danushka Bollegala
Our proposed method can combine source sense embeddings that cover different sets of word senses.
no code implementations • 21 May 2022 • Jin Xu, Weiqi Wang, Zheming Gao, Haochen Luo, Qian Wu
We then propose a delay prediction model based on non-homogeneous Markov chains.
no code implementations • 3 Jan 2021 • Shen Jia, Yulin Zhang, Yiming Mao, Jiawei Gao, Yixuan Chen, YuXuan Jiang, Haochen Luo, Kebo Lv, Jionglong Su
The biological functions in cancer development of 50 selected genes is also explored through enrichment analysis and the results show that 12 out of 16 of our top features have already been identified to be specific with cancer and we also propose some more genes to be tested for future studies.