Zobrazeno 1 - 10
of 1 468
pro vyhledávání: '"Li, Longfei"'
Large Language Models (LLMs) have shown impressive performance in natural language tasks, but their outputs can exhibit undesirable attributes or biases. Existing methods for steering LLMs toward desired attributes often assume unbiased representatio
Externí odkaz:
http://arxiv.org/abs/2405.04160
Autor:
Cheng, Mingyue, Zhang, Hao, Liu, Qi, Yuan, Fajie, Li, Zhi, Huang, Zhenya, Chen, Enhong, Zhou, Jun, Li, Longfei
Sequential recommender systems (SRS) could capture dynamic user preferences by modeling historical behaviors ordered in time. Despite effectiveness, focusing only on the \textit{collaborative signals} from behaviors does not fully grasp user interest
Externí odkaz:
http://arxiv.org/abs/2403.07623
The advent of large language models (LLMs) such as ChatGPT, PaLM, and GPT-4 has catalyzed remarkable advances in natural language processing, demonstrating human-like language fluency and reasoning capacities. This position paper introduces the conce
Externí odkaz:
http://arxiv.org/abs/2402.03628
The anomalous Hall and Nernst effects describe the voltage drop perpendicular to an applied current and temperature gradient due to the magnetization of a magnetic material. These effects can be utilized to measure the Berry curvature at the Fermi en
Externí odkaz:
http://arxiv.org/abs/2401.17624
As personalized recommendation systems become vital in the age of information overload, traditional methods relying solely on historical user interactions often fail to fully capture the multifaceted nature of human interests. To enable more human-ce
Externí odkaz:
http://arxiv.org/abs/2401.08217
Autor:
Li, Longfei, Yang, Mingcheng
A fluid in contact with a flat structureless wall constitutes the simplest interface system, but the fluid-wall interfacial tension cannot be trivially and even unequivocally determined due to the ambiguity in identifying the precise location of flui
Externí odkaz:
http://arxiv.org/abs/2312.14714
Since artificial intelligence has seen tremendous recent successes in many areas, it has sparked great interest in its potential for trustworthy and interpretable risk prediction. However, most models lack causal reasoning and struggle with class imb
Externí odkaz:
http://arxiv.org/abs/2312.16113
Spectral unmixing is a significant challenge in hyperspectral image processing. Existing unmixing methods utilize prior knowledge about the abundance distribution to solve the regularization optimization problem, where the difficulty lies in choosing
Externí odkaz:
http://arxiv.org/abs/2312.13127
Autor:
Guan, Yanchu, Wang, Dong, Chu, Zhixuan, Wang, Shiyu, Ni, Feiyue, Song, Ruihua, Li, Longfei, Gu, Jinjie, Zhuang, Chenyi
While intelligent virtual assistants like Siri, Alexa, and Google Assistant have become ubiquitous in modern life, they still face limitations in their ability to follow multi-step instructions and accomplish complex goals articulated in natural lang
Externí odkaz:
http://arxiv.org/abs/2312.06677
Autor:
Chu, Zhixuan, Guo, Huaiyu, Zhou, Xinyuan, Wang, Yijia, Yu, Fei, Chen, Hong, Xu, Wanqing, Lu, Xin, Cui, Qing, Li, Longfei, Zhou, Jun, Li, Sheng
Large language models (LLMs) show promise for natural language tasks but struggle when applied directly to complex domains like finance. LLMs have difficulty reasoning about and integrating all relevant information. We propose a data-centric approach
Externí odkaz:
http://arxiv.org/abs/2310.17784