no code implementations • NAACL (ALVR) 2021 • Chengxi Li, Brent Harrison
In this paper, we propose an error causal inference method that could be used for finding dominant features for a faulty instance under a well-trained multi-modality input model, which could apply to any testing instance.
1 code implementation • 22 Apr 2024 • Boning Zhang, Chengxi Li, Kai Fan
Large language models (LLMs) have been explored in a variety of reasoning tasks including solving of mathematical problems.
no code implementations • 31 Mar 2024 • Shudi Weng, Chengxi Li, Ming Xiao, Mikael Skoglund
We investigate federated learning (FL) in the presence of stragglers, with emphasis on wireless scenarios where the power-constrained edge devices collaboratively train a global model on their local datasets and transmit local model updates through fading channels.
no code implementations • 22 Mar 2024 • Chengxi Li, Ming Xiao, Mikael Skoglund
In ACFL, before the training, each device uploads a coded local dataset with additive noise to the central server to generate a global coded dataset under privacy preservation requirements.
no code implementations • 19 Mar 2024 • Chengxi Li, Mikael Skoglund
For this problem, DL methods based on gradient coding have been widely investigated, which redundantly distribute the training data to the workers to guarantee convergence when some workers are stragglers.
no code implementations • 6 Feb 2024 • Chengxi Li, Mikael Skoglund
In this paper, we consider a decentralized learning problem in the presence of stragglers.
1 code implementation • 16 Jan 2024 • Minpeng Liao, Wei Luo, Chengxi Li, Jing Wu, Kai Fan
Large language models (LLMs) have seen considerable advancements in natural language understanding tasks, yet there remains a gap to bridge before attaining true artificial general intelligence, especially concerning shortcomings in mathematical reasoning capabilities.
no code implementations • 3 Apr 2023 • Chengxi Li, Gang Li, Zhuoyue Wang, Xueqian Wang, Pramod K. Varshney
For this problem, an unsupervised change detection method has been proposed recently based on the image translation technique of Cycle-Consistent Adversarial Networks (CycleGANs), where one image is translated from its original modality to the modality of the other image so that the difference map can be obtained by performing arithmetical subtraction.
no code implementations • 28 Mar 2023 • Chengxi Li, Kai Fan, Jiajun Bu, Boxing Chen, Zhongqiang Huang, Zhi Yu
Song translation requires both translation of lyrics and alignment of music notes so that the resulting verse can be sung to the accompanying melody, which is a challenging problem that has attracted some interests in different aspects of the translation process.
1 code implementation • 18 Nov 2022 • Yuhang Lai, Chengxi Li, Yiming Wang, Tianyi Zhang, Ruiqi Zhong, Luke Zettlemoyer, Scott Wen-tau Yih, Daniel Fried, Sida Wang, Tao Yu
We introduce DS-1000, a code generation benchmark with a thousand data science problems spanning seven Python libraries, such as NumPy and Pandas.
1 code implementation • 27 Sep 2022 • Xiatao Kang, Ping Li, Jiayi Yao, Chengxi Li
Pruning on neural networks before training not only compresses the original models, but also accelerates the network training phase, which has substantial application value.
3 code implementations • ACL 2022 • Jinglin Liu, Chengxi Li, Yi Ren, Zhiying Zhu, Zhou Zhao
Furthermore, we propose a latent-mapping algorithm in the latent space to convert the amateur vocal tone to the professional one.
no code implementations • 4 Jan 2022 • Chengxi Li, Brent Harrison
In this paper, we build two automatic evaluation metrics for evaluating the association between a machine-generated caption and a ground truth stylized caption: OnlyStyle and StyleCIDEr.
no code implementations • 20 Oct 2021 • Chengxi Li, Brent Harrison
In this paper, we propose to build a stylish image captioning model through a Multi-style Multi modality mechanism (2M).
no code implementations • 17 Sep 2021 • Chengxi Li, Feiyu Gao, Jiajun Bu, Lu Xu, Xiang Chen, Yu Gu, Zirui Shao, Qi Zheng, Ningyu Zhang, Yongpan Wang, Zhi Yu
We inject sentiment knowledge regarding aspects, opinions, and polarities into prompt and explicitly model term relations via constructing consistency and polarity judgment templates from the ground truth triplets.
Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +3
no code implementations • 24 Jun 2021 • Chengxi Li, Stanley H. Chan, Yi-Ting Chen
Identification of high-risk driving situations is generally approached through collision risk estimation or accident pattern recognition.
7 code implementations • 6 May 2021 • Jinglin Liu, Chengxi Li, Yi Ren, Feiyang Chen, Zhou Zhao
Singing voice synthesis (SVS) systems are built to synthesize high-quality and expressive singing voice, in which the acoustic model generates the acoustic features (e. g., mel-spectrogram) given a music score.
no code implementations • 20 Mar 2021 • Chengxi Li, Brent Harrison
In this paper, we build a multi-style generative model for stylish image captioning which uses multi-modality image features, ResNeXt features and text features generated by DenseCap.
no code implementations • 24 Dec 2020 • Chengxi Li, Gang Li, Pramod K. Varshney
In this paper, we investigate the problem of decentralized federated learning (DFL) in Internet of things (IoT) systems, where a number of IoT clients train models collectively for a common task without sharing their private training data in the absence of a central server.
no code implementations • 9 Mar 2020 • Xixi Zhou, Chengxi Li, Jiajun Bu, Chengwei Yao, Keyue Shi, Zhi Yu, Zhou Yu
Our approach, Text matching with Deep Info Max (TIM), is integrated with a procedure of unsupervised learning of representations by maximizing the mutual information between text matching neural network's input and output.
no code implementations • 5 Mar 2020 • Chengxi Li, Stanley H. Chan, Yi-Ting Chen
We formulate the task as the cause-effect problem and present a novel two-stage risk object identification framework based on causal inference with the proposed object-level manipulable driving model.
no code implementations • 25 Nov 2019 • Xiyuan Zhang, Chengxi Li, Dian Yu, Samuel Davidson, Zhou Yu
We then train a prediction model using both utterances containing ellipsis and our automatically completed utterances.
no code implementations • 20 Sep 2019 • Chengxi Li, Yue Meng, Stanley H. Chan, Yi-Ting Chen
First, we decompose egocentric interactions into ego-thing and ego-stuff interaction, modeled by two GCNs.