no code implementations • 21 Feb 2024 • Mingxuan Xiao, Yan Xiao, Hai Dong, Shunhui Ji, Pengcheng Zhang
To our knowledge, RITFIS is the first framework designed to assess the robustness of LLM-based intelligent software against natural language inputs.
1 code implementation • 22 Aug 2023 • Mingxuan Xiao, Yan Xiao, Hai Dong, Shunhui Ji, Pengcheng Zhang
The widespread adoption of DNNs in NLP software has highlighted the need for robustness.
1 code implementation • 17 Jul 2023 • Hanbo Cai, Pengcheng Zhang, Hai Dong, Yan Xiao, Stefanos Koffas, Yiming Li
Motivated by these findings, we propose to exploit elements of sound ($e. g.$, pitch and timbre) to design more stealthy yet effective poison-only backdoor attacks.
no code implementations • 12 Jul 2023 • Nithin Raghavan, Yan Xiao, Kai-En Lin, Tiancheng Sun, Sai Bi, Zexiang Xu, Tzu-Mao Li, Ravi Ramamoorthi
In this paper, we demonstrate a hybrid neural-wavelet PRT solution to high-frequency indirect illumination, including glossy reflection, for relighting with changing view.
no code implementations • 20 Dec 2022 • Hanbo Cai, Pengcheng Zhang, Hai Dong, Yan Xiao, Shunhui Ji
Keyword spotting (KWS) based on deep neural networks (DNNs) has achieved massive success in voice control scenarios.
no code implementations • 16 Nov 2022 • Hanbo Cai, Pengcheng Zhang, Hai Dong, Yan Xiao, Shunhui Ji
The training of KWS is usually based on deep neural networks and requires a large amount of data.
no code implementations • 24 Jun 2022 • Mark Huasong Meng, Guangdong Bai, Sin Gee Teo, Zhe Hou, Yan Xiao, Yun Lin, Jin Song Dong
For those reasons, there is a high demand for trustworthy and rigorous methods to verify the robustness of neural network models.
1 code implementation • 6 Oct 2021 • Yan Xiao, Yun Lin, Ivan Beschastnikh, Changsheng Sun, David S. Rosenblum, Jin Song Dong
However, inputs may deviate from the training dataset distribution in real deployments.
1 code implementation • 10 Aug 2021 • Yubo Xie, Zonghui Liu, Zongyang Ma, Fanyuan Meng, Yan Xiao, Fahui Miao, Pearl Pu
Commonsense knowledge is essential for advancing natural language processing (NLP) by enabling models to engage in human-like reasoning, which requires a deeper understanding of context and often involves making inferences based on implicit external knowledge.
no code implementations • 10 Jan 2021 • Yan Xiao, Yaochu Jin, Kuangrong Hao
First, based on the prototypical networks, we propose an adaptive mixture mechanism to add label words to the representation of the class prototype, which, to the best of our knowledge, is the first attempt to integrate the label information into features of the support samples of each class so as to get more interactive class prototypes.
no code implementations • 5 Sep 2020 • Jiakang Bao, Yang-Hui He, Yan Xiao
We study chiral rings of 4d $\mathcal{N}=1$ supersymmetric gauge theories via the notion of K-stability.
High Energy Physics - Theory Algebraic Geometry
no code implementations • 10 Mar 2020 • Yan Xiao, Yaochu Jin, Ran Cheng, Kuangrong Hao
With an exponential explosive growth of various digital text information, it is challenging to efficiently obtain specific knowledge from massive unstructured text information.
5 code implementations • ACL 2019 • Jiaqi Guo, Zecheng Zhan, Yan Gao, Yan Xiao, Jian-Guang Lou, Ting Liu, Dongmei Zhang
We present a neural approach called IRNet for complex and cross-domain Text-to-SQL.