no code implementations • 26 Feb 2024 • Han Wang, Sijia Yu, Chunyang Chen, Burak Turhan, Xiaodong Zhu
Deep Learning (DL) models have rapidly advanced, focusing on achieving high performance through testing model accuracy and robustness.
no code implementations • 29 Jan 2024 • Jian Gu, Aldeida Aleti, Chunyang Chen, Hongyu Zhang
In response, we introduce a pioneering method called vocabulary-defined semantics, which establishes a reference frame within the LM latent space, ensuring disentangled semantic analysis grounded in LM vocabulary.
no code implementations • 8 Dec 2023 • Jian Gu, Aldeida Aleti, Chunyang Chen, Hongyu Zhang
In this paper, we propose a novel and effective model editing approach, \textsc{MENT}, to patch LLMs in coding tasks.
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 • 7 Jun 2023 • Mengyu Chen, Zhenchang Xing, Jieshan Chen, Chunyang Chen, Qinghua Lu
Although their capabilities of processing user intents have been developed rapidly, virtual assistants in most platforms are only capable of handling pre-defined high-level tasks supported by extra manual efforts of developers.
1 code implementation • NeurIPS 2023 • Xin Zheng, Miao Zhang, Chunyang Chen, Quoc Viet Hung Nguyen, Xingquan Zhu, Shirui Pan
Specifically, SFGC contains two collaborative components: (1) a training trajectory meta-matching scheme for effectively synthesizing small-scale graph-free data; (2) a graph neural feature score metric for dynamically evaluating the quality of the condensed data.
no code implementations • 23 Feb 2023 • Xin Zheng, Miao Zhang, Chunyang Chen, Qin Zhang, Chuan Zhou, Shirui Pan
Therefore, in this paper, we propose a novel automated graph neural network on heterophilic graphs, namely Auto-HeG, to automatically build heterophilic GNN models with expressive learning abilities.
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, 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.
1 code implementation • 15 Jun 2022 • Mulong Xie, Zhenchang Xing, Sidong Feng, Chunyang Chen, Liming Zhu, Xiwei Xu
These principles are domain-independent and have been widely adopted by practitioners to structure content on GUIs to improve aesthetic pleasant and usability.
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 • 1 Feb 2021 • Kaibo Cao, Chunyang Chen, Sebastian Baltes, Christoph Treude, Xiang Chen
As query reformulation is tedious for developers, especially for novices, we propose an automated software-specific query reformulation approach based on deep learning.
1 code implementation • 25 Jan 2021 • Tianming Zhao, Chunyang Chen, Yuanning Liu, Xiaodong Zhu
Graphical User Interface (GUI) is ubiquitous in almost all modern desktop software, mobile applications, and online websites.
no code implementations • 18 Jan 2021 • Yuanchun Li, Jiayi Hua, Haoyu Wang, Chunyang Chen, Yunxin Liu
The core of the attack is a neural conditional branch constructed with a trigger detector and several operators and injected into the victim model as a malicious payload.
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.
2 code implementations • 12 Aug 2020 • Jieshan Chen, Mulong Xie, Zhenchang Xing, Chunyang Chen, Xiwei Xu, Liming Zhu, Guoqiang Li
We conduct the first large-scale empirical study of seven representative GUI element detection methods on over 50k GUI images to understand the capabilities, limitations and effective designs of these methods.
1 code implementation • 1 Mar 2020 • Jieshan Chen, Chunyang Chen, Zhenchang Xing, Xiwei Xu, Liming Zhu, Guoqiang Li, Jinshui Wang
However, the prerequisite of using screen readers is that developers have to add natural-language labels to the image-based components when they are developing the app.
no code implementations • 20 Mar 2018 • Lei Ma, Felix Juefei-Xu, Fuyuan Zhang, Jiyuan Sun, Minhui Xue, Bo Li, Chunyang Chen, Ting Su, Li Li, Yang Liu, Jianjun Zhao, Yadong Wang
Deep learning (DL) defines a new data-driven programming paradigm that constructs the internal system logic of a crafted neuron network through a set of training data.