Zobrazeno 1 - 10
of 339
pro vyhledávání: '"Yan Yuchen"'
Autor:
Zhu, Senbin, He, Chenyuan, Liu, Hongde, Dong, Pengcheng, Zhao, Hanjie, Yan, Yuchen, Jia, Yuxiang, Zan, Hongying, Peng, Min
In recent years, fine-grained sentiment analysis in finance has gained significant attention, but the scarcity of entity-level datasets remains a key challenge. To address this, we have constructed the largest English and Chinese financial entity-lev
Externí odkaz:
http://arxiv.org/abs/2412.19140
Autor:
Yan, Yuchen, Chen, Yuzhong, Chen, Huiyuan, Li, Xiaoting, Xu, Zhe, Zeng, Zhichen, Liu, Zhining, Tong, Hanghang
Graph Neural Networks (GNNs) have exhibited remarkable efficacy in diverse graph learning tasks, particularly on static homophilic graphs. Recent attention has pivoted towards more intricate structures, encompassing (1) static heterophilic graphs enc
Externí odkaz:
http://arxiv.org/abs/2412.16435
Autor:
Jiang, Jin, Yan, Yuchen, Liu, Yang, Jin, Yonggang, Peng, Shuai, Zhang, Mengdi, Cai, Xunliang, Cao, Yixin, Gao, Liangcai, Tang, Zhi
In this paper, we present a novel approach, called LogicPro, to enhance Large Language Models (LLMs) complex Logical reasoning through Program Examples. We do this effectively by simply utilizing widely available algorithmic problems and their code s
Externí odkaz:
http://arxiv.org/abs/2409.12929
Autor:
Yan, Yuchen, Jiang, Jin, Liu, Yang, Cao, Yixin, Xu, Xin, zhang, Mengdi, Cai, Xunliang, Shao, Jian
Self-correction is a novel method that can stimulate the potential reasoning abilities of large language models (LLMs). It involves detecting and correcting errors during the inference process when LLMs solve reasoning problems. However, recent works
Externí odkaz:
http://arxiv.org/abs/2409.01524
Autor:
Long, Qingqing, Yan, Yuchen, Zhang, Peiyan, Fang, Chen, Cui, Wentao, Ning, Zhiyuan, Xiao, Meng, Cao, Ning, Luo, Xiao, Xu, Lingjun, Jiang, Shiyue, Fang, Zheng, Chen, Chong, Hua, Xian-Sheng, Zhou, Yuanchun
Large-scale "pre-train and prompt learning" paradigms have demonstrated remarkable adaptability, enabling broad applications across diverse domains such as question answering, image recognition, and multimodal retrieval. This approach fully leverages
Externí odkaz:
http://arxiv.org/abs/2408.14520
Quotations in literary works, especially novels, are important to create characters, reflect character relationships, and drive plot development. Current research on quotation extraction in novels primarily focuses on quotation attribution, i.e., ide
Externí odkaz:
http://arxiv.org/abs/2408.09452
Autor:
Yang, Xiaodong, Chen, Huiyuan, Yan, Yuchen, Tang, Yuxin, Zhao, Yuying, Xu, Eric, Cai, Yiwei, Tong, Hanghang
The learning objective is integral to collaborative filtering systems, where the Bayesian Personalized Ranking (BPR) loss is widely used for learning informative backbones. However, BPR often experiences slow convergence and suboptimal local optima,
Externí odkaz:
http://arxiv.org/abs/2406.16170
Autor:
Zhang, Tianle, Ma, Langtian, Yan, Yuchen, Zhang, Yuchen, Wang, Kai, Yang, Yue, Guo, Ziyao, Shao, Wenqi, You, Yang, Qiao, Yu, Luo, Ping, Zhang, Kaipeng
Recent text-to-video (T2V) technology advancements, as demonstrated by models such as Gen2, Pika, and Sora, have significantly broadened its applicability and popularity. Despite these strides, evaluating these models poses substantial challenges. Pr
Externí odkaz:
http://arxiv.org/abs/2406.08845
Autor:
Zhang, Peiyan, Yan, Yuchen, Zhang, Xi, Kang, Liying, Li, Chaozhuo, Huang, Feiran, Wang, Senzhang, Kim, Sunghun
In the realm of personalized recommender systems, the challenge of adapting to evolving user preferences and the continuous influx of new users and items is paramount. Conventional models, typically reliant on a static training-test approach, struggl
Externí odkaz:
http://arxiv.org/abs/2406.08229
Autor:
Zong, Chang, Yan, Yuchen, Lu, Weiming, Shao, Jian, Huang, Eliot, Chang, Heng, Zhuang, Yueting
Recent progress with LLM-based agents has shown promising results across various tasks. However, their use in answering questions from knowledge bases remains largely unexplored. Implementing a KBQA system using traditional methods is challenging due
Externí odkaz:
http://arxiv.org/abs/2402.14320