2 code implementations • NeurIPS 2023 • Han Hu, Haolan Zhan, Yujin Huang, Di Liu
There are currently several publicly accessible GUI page datasets for phones, but none for pairwise GUIs between phones and tablets.
no code implementations • 3 Jul 2023 • Jason Ching Yuen Siu, Jieshan Chen, Yujin Huang, Zhenchang Xing, Chunyang Chen
We further implemented our findings into a multi-faceted search-enabled gallery.
no code implementations • 6 May 2023 • Ye Sang, Yujin Huang, Shuo Huang, Helei Cui
In particular, our attack could influence the performance and latency of the model without affecting the operation of a DL app.
no code implementations • 6 May 2023 • Zijian Wang, Shuo Huang, Yujin Huang, Helei Cui
In recent years, on-device deep learning has gained attention as a means of developing affordable deep learning applications for mobile devices.
1 code implementation • 8 Feb 2023 • Yujin Huang, Terry Yue Zhuo, Qiongkai Xu, Han Hu, Xingliang Yuan, Chunyang Chen
In this work, we propose Training-Free Lexical Backdoor Attack (TFLexAttack) as the first training-free backdoor attack on language models.
no code implementations • 30 Jan 2023 • Terry Yue Zhuo, Zhuang Li, Yujin Huang, Fatemeh Shiri, Weiqing Wang, Gholamreza Haffari, Yuan-Fang Li
Semantic parsing is a technique aimed at constructing a structured representation of the meaning of a natural-language question.
no code implementations • 30 Jan 2023 • Terry Yue Zhuo, Yujin Huang, Chunyang Chen, Zhenchang Xing
We believe that our findings may give light on future efforts to determine and mitigate the ethical hazards posed by machines in LLM applications.
no code implementations • 23 Dec 2022 • Fucai Ke, Weiqing Wang, Weicong Tan, Lan Du, Yuan Jin, Yujin Huang, Hongzhi Yin
Knowledge tracing (KT) aims to leverage students' learning histories to estimate their mastery levels on a set of pre-defined skills, based on which the corresponding future performance can be accurately predicted.
1 code implementation • 23 Apr 2022 • Yujin Huang, Chunyang Chen
We evaluate the attack effectiveness and generality in terms of four different settings including pre-trained models, datasets, transfer learning approaches and adversarial attack algorithms.
1 code implementation • 12 Jan 2021 • Yujin Huang, Han Hu, Chunyang Chen
Deep learning has shown its power in many applications, including object detection in images, natural-language understanding, and speech recognition.