Zobrazeno 1 - 10
of 178
pro vyhledávání: '"LIU Zhining"'
Publikováno v:
Guan'gai paishui xuebao, Vol 41, Iss 8, Pp 87-94 (2022)
【Objective】 Bioretention is a method to purify water, and the aim of this paper is to study its effect on stormwater runoff. 【Method】 We took stormwater runoff in Shijiazhuang city as an example, investigating the outflow characteristics of t
Externí odkaz:
https://doaj.org/article/3511e81589214d3494f9e1f6b7337d10
Powerful as they are, graph neural networks (GNNs) are known to be vulnerable to distribution shifts. Recently, test-time adaptation (TTA) has attracted attention due to its ability to adapt a pre-trained model to a target domain without re-accessing
Externí odkaz:
http://arxiv.org/abs/2410.06976
Autor:
Chen, Lingjie, Qiu, Ruizhong, Yuan, Siyu, Liu, Zhining, Wei, Tianxin, Yoo, Hyunsik, Zeng, Zhichen, Yang, Deqing, Tong, Hanghang
Watermarking of large language models (LLMs) generation embeds an imperceptible statistical pattern within texts, making it algorithmically detectable. Watermarking is a promising method for addressing potential harm and biases from LLMs, as it enabl
Externí odkaz:
http://arxiv.org/abs/2410.06467
Multivariate Time Series (MTS) forecasting is a fundamental task with numerous real-world applications, such as transportation, climate, and epidemiology. While a myriad of powerful deep learning models have been developed for this task, few works ha
Externí odkaz:
http://arxiv.org/abs/2410.02195
Data collected in the real world often encapsulates historical discrimination against disadvantaged groups and individuals. Existing fair machine learning (FairML) research has predominantly focused on mitigating discriminative bias in the model pred
Externí odkaz:
http://arxiv.org/abs/2406.08819
Position bias, i.e., users' preference of an item is affected by its placing position, is well studied in the recommender system literature. However, most existing methods ignore the widely coupled ranking bias, which is also related to the placing p
Externí odkaz:
http://arxiv.org/abs/2405.18971
Autor:
Xie, Zhitian, Zhang, Yinger, Zhuang, Chenyi, Shi, Qitao, Liu, Zhining, Gu, Jinjie, Zhang, Guannan
The application of mixture-of-experts (MoE) is gaining popularity due to its ability to improve model's performance. In an MoE structure, the gate layer plays a significant role in distinguishing and routing input features to different experts. This
Externí odkaz:
http://arxiv.org/abs/2402.00893
Autor:
Lu, Xingyu, Liu, Zhining, Guan, Yanchu, Zhang, Hongxuan, Zhuang, Chenyi, Ma, Wenqi, Tan, Yize, Gu, Jinjie, Zhang, Guannan
Publikováno v:
Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence AI for Good. Pages 6103-6111
Given the enormous number of users and items, industrial cascade recommendation systems (RS) are continuously expanded in size and complexity to deliver relevant items, such as news, services, and commodities, to the appropriate users. In a real-worl
Externí odkaz:
http://arxiv.org/abs/2312.16176
In this article, we study the orbifold fundamental group $\pi_1^{\rm reg}(X,\Delta)$ of a log Calabi--Yau pair $(X,\Delta)$. We conjecture that the orbifold fundamental group $\pi_1^{\rm orb}(X,\Delta)$ of a $n$-dimensional log Calabi--Yau pair admit
Externí odkaz:
http://arxiv.org/abs/2312.03981
Autor:
Zhang, Hongxuan, Liu, Zhining, Zhao, Yao, Zheng, Jiaqi, Zhuang, Chenyi, Gu, Jinjie, Chen, Guihai
In this work, we propose FastCoT, a model-agnostic framework based on parallel decoding without any further training of an auxiliary model or modification to the LLM itself. FastCoT uses a size-varying context window whose size changes with position
Externí odkaz:
http://arxiv.org/abs/2311.08263