Zobrazeno 1 - 10
of 24
pro vyhledávání: '"Dong, Xinshuai"'
Autor:
Song, Xiangchen, Li, Zijian, Chen, Guangyi, Zheng, Yujia, Fan, Yewen, Dong, Xinshuai, Zhang, Kun
Causal Temporal Representation Learning (Ctrl) methods aim to identify the temporal causal dynamics of complex nonstationary temporal sequences. Despite the success of existing Ctrl methods, they require either directly observing the domain variables
Externí odkaz:
http://arxiv.org/abs/2409.03142
Independent component analysis (ICA) is a fundamental statistical tool used to reveal hidden generative processes from observed data. However, traditional ICA approaches struggle with the rotational invariance inherent in Gaussian distributions, ofte
Externí odkaz:
http://arxiv.org/abs/2408.10353
Autor:
Dong, Xinshuai, Ng, Ignavier, Huang, Biwei, Sun, Yuewen, Jin, Songyao, Legaspi, Roberto, Spirtes, Peter, Zhang, Kun
Linear causal models are important tools for modeling causal dependencies and yet in practice, only a subset of the variables can be observed. In this paper, we examine the parameter identifiability of these models by investigating whether the edge c
Externí odkaz:
http://arxiv.org/abs/2407.16975
MAMA: Meta-optimized Angular Margin Contrastive Framework for Video-Language Representation Learning
Autor:
Nguyen, Thong, Bin, Yi, Wu, Xiaobao, Dong, Xinshuai, Hu, Zhiyuan, Le, Khoi, Nguyen, Cong-Duy, Ng, See-Kiong, Tuan, Luu Anh
Data quality stands at the forefront of deciding the effectiveness of video-language representation learning. However, video-text pairs in previous data typically do not align perfectly with each other, which might lead to video-language representati
Externí odkaz:
http://arxiv.org/abs/2407.03788
Dynamic topic models track the evolution of topics in sequential documents, which have derived various applications like trend analysis and opinion mining. However, existing models suffer from repetitive topic and unassociated topic issues, failing t
Externí odkaz:
http://arxiv.org/abs/2405.17957
Autor:
Zeng, Donghuo, Legaspi, Roberto S., Sun, Yuewen, Dong, Xinshuai, Ikeda, Kazushi, Spirtes, Peter, Zhang, kun
Customizing persuasive conversations related to the outcome of interest for specific users achieves better persuasion results. However, existing persuasive conversation systems rely on persuasive strategies and encounter challenges in dynamically adj
Externí odkaz:
http://arxiv.org/abs/2404.13792
Recent representation learning approaches enhance neural topic models by optimizing the weighted linear combination of the evidence lower bound (ELBO) of the log-likelihood and the contrastive learning objective that contrasts pairs of input document
Externí odkaz:
http://arxiv.org/abs/2402.07577
Financial data is generally time series in essence and thus suffers from three fundamental issues: the mismatch in time resolution, the time-varying property of the distribution - nonstationarity, and causal factors that are important but unknown/uno
Externí odkaz:
http://arxiv.org/abs/2401.05414
Autor:
Dong, Xinshuai, Huang, Biwei, Ng, Ignavier, Song, Xiangchen, Zheng, Yujia, Jin, Songyao, Legaspi, Roberto, Spirtes, Peter, Zhang, Kun
Most existing causal discovery methods rely on the assumption of no latent confounders, limiting their applicability in solving real-life problems. In this paper, we introduce a novel, versatile framework for causal discovery that accommodates the pr
Externí odkaz:
http://arxiv.org/abs/2312.11001
Autor:
Nguyen, Thong, Wu, Xiaobao, Dong, Xinshuai, Le, Khoi, Hu, Zhiyuan, Nguyen, Cong-Duy, Ng, See-Kiong, Tuan, Luu Anh
Fully fine-tuning pretrained large-scale transformer models has become a popular paradigm for video-language modeling tasks, such as temporal language grounding and video-language summarization. With a growing number of tasks and limited training dat
Externí odkaz:
http://arxiv.org/abs/2312.06950