Zobrazeno 1 - 10
of 4 233
pro vyhledávání: '"Zhu, He"'
Autor:
Deng, Ken, Liu, Jiaheng, Zhu, He, Liu, Congnan, Li, Jingxin, Wang, Jiakai, Zhao, Peng, Zhang, Chenchen, Wu, Yanan, Yin, Xueqiao, Zhang, Yuanxing, Su, Wenbo, Xiang, Bangyu, Ge, Tiezheng, Zheng, Bo
Code completion models have made significant progress in recent years. Recently, repository-level code completion has drawn more attention in modern software development, and several baseline methods and benchmarks have been proposed. However, existi
Externí odkaz:
http://arxiv.org/abs/2406.01359
Autor:
Ji, Yuzhou, Zhu, He, Tang, Junshu, Liu, Wuyi, Zhang, Zhizhong, Xie, Yuan, Ma, Lizhuang, Tan, Xin
The semantically interactive radiance field has always been an appealing task for its potential to facilitate user-friendly and automated real-world 3D scene understanding applications. However, it is a challenging task to achieve high quality, effic
Externí odkaz:
http://arxiv.org/abs/2406.01916
Autor:
Zhu, He, Xiao, Yunlong, Yu, Zhongyang, Zhu, Jiaqi, Li, Qing, Ye, Zhenyu, Wang, Xi, Liu, Changlong, Pan, Changyu, Shan, Yufeng, Duan, Junli, Wu, Huizhen, Hu, Weida, Dai, Ning
Mid-infrared spectrum is a critical tool for chemical analysis, industrial inspection, environment, and other fields due to its rich chemical bond information. However, the complicated growth or fabrication procedures of existing mid-infrared sensiti
Externí odkaz:
http://arxiv.org/abs/2405.02668
HILL: Hierarchy-aware Information Lossless Contrastive Learning for Hierarchical Text Classification
Existing self-supervised methods in natural language processing (NLP), especially hierarchical text classification (HTC), mainly focus on self-supervised contrastive learning, extremely relying on human-designed augmentation rules to generate contras
Externí odkaz:
http://arxiv.org/abs/2403.17307
Autor:
Zhu, He, Zhang, Wenjia, Huang, Nuoxian, Li, Boyang, Niu, Luyao, Fan, Zipei, Lun, Tianle, Tao, Yicheng, Su, Junyou, Gong, Zhaoya, Fang, Chenyu, Liu, Xing
In the field of urban planning, general-purpose large language models often struggle to meet the specific needs of planners. Tasks like generating urban planning texts, retrieving related information, and evaluating planning documents pose unique cha
Externí odkaz:
http://arxiv.org/abs/2402.19273
We present a novel prompt-based personalized federated learning (pFL) method to address data heterogeneity and privacy concerns in traditional medical visual question answering (VQA) methods. Specifically, we regard medical datasets from different or
Externí odkaz:
http://arxiv.org/abs/2402.09677
Learning time-series representations for discriminative tasks has been a long-standing challenge. Current pre-training methods are limited in either unidirectional next-token prediction or randomly masked token prediction. We propose a novel architec
Externí odkaz:
http://arxiv.org/abs/2402.09558
Recent advancements on Large Language Models (LLMs) enable AI Agents to automatically generate and execute multi-step plans to solve complex tasks. However, since LLM's content generation process is hardly controllable, current LLM-based agents frequ
Externí odkaz:
http://arxiv.org/abs/2402.00798
This paper addresses the challenge of 3D instance segmentation by simultaneously leveraging 3D geometric and multi-view image information. Many previous works have applied deep learning techniques to 3D point clouds for instance segmentation. However
Externí odkaz:
http://arxiv.org/abs/2312.08372
Attention has become a common ingredient in deep learning architectures. It adds a dynamical selection of information on top of the static selection of information supported by weights. In the same way, we can imagine a higher-order informational fil
Externí odkaz:
http://arxiv.org/abs/2305.17375