Zobrazeno 1 - 10
of 32
pro vyhledávání: '"Ou, Zijing"'
Estimating mutual information (MI) is a fundamental yet challenging task in data science and machine learning. This work proposes a new estimator for mutual information. Our main discovery is that a preliminary estimate of the data distribution can d
Externí odkaz:
http://arxiv.org/abs/2408.09377
Augmenting Large Language Models (LLMs) with retrieved external knowledge has proven effective for improving the factual accuracy of generated responses. Despite their success, retrieval-augmented LLMs still face the distractibility issue, where the
Externí odkaz:
http://arxiv.org/abs/2406.17519
The probabilistic diffusion model has become highly effective across various domains. Typically, sampling from a diffusion model involves using a denoising distribution characterized by a Gaussian with a learned mean and either fixed or learned covar
Externí odkaz:
http://arxiv.org/abs/2406.10808
Training energy-based models (EBMs) on discrete spaces is challenging because sampling over such spaces can be difficult. We propose to train discrete EBMs with energy discrepancy (ED), a novel type of contrastive loss functional which only requires
Externí odkaz:
http://arxiv.org/abs/2307.07595
Autor:
Schröder, Tobias, Ou, Zijing, Lim, Jen Ning, Li, Yingzhen, Vollmer, Sebastian J., Duncan, Andrew B.
Energy-based models are a simple yet powerful class of probabilistic models, but their widespread adoption has been limited by the computational burden of training them. We propose a novel loss function called Energy Discrepancy (ED) which does not r
Externí odkaz:
http://arxiv.org/abs/2307.06431
Autor:
Jiang, Wangjie, Ye, Zhihao, Ou, Zijing, Zhao, Ruihui, Zheng, Jianguang, Liu, Yi, Li, Siheng, Liu, Bang, Yang, Yujiu, Zheng, Yefeng
Chinese Spelling Correction (CSC) is gaining increasing attention due to its promise of automatically detecting and correcting spelling errors in Chinese texts. Despite its extensive use in many applications, like search engines and optical character
Externí odkaz:
http://arxiv.org/abs/2210.11720
Publikováno v:
Cailiao gongcheng, Vol 52, Iss 3, Pp 109-116 (2024)
The foaming agent alkyl polyglucoside was added into graphene oxide dispersion to generate graphene oxide microbubble agglomerates, which were then combined with polyurethane sponge skeleton through impregnating, the as-obtained composite sponge was
Externí odkaz:
https://doaj.org/article/7af2ad5ca83b46caa8ff35e26d7e2ec7
A key challenge in video question answering is how to realize the cross-modal semantic alignment between textual concepts and corresponding visual objects. Existing methods mostly seek to align the word representations with the video regions. However
Externí odkaz:
http://arxiv.org/abs/2205.06530
Learning neural set functions becomes increasingly more important in many applications like product recommendation and compound selection in AI-aided drug discovery. The majority of existing works study methodologies of set function learning under th
Externí odkaz:
http://arxiv.org/abs/2203.01693
Publikováno v:
In Progress in Organic Coatings October 2024 195