Zobrazeno 1 - 10
of 3 639
pro vyhledávání: '"Wu, JianHua"'
Autor:
Fan, Jiaqi, Wu, Jianhua, Gao, Jincheng, Yu, Jianhao, Wang, Yafei, Chu, Hongqing, Gao, Bingzhao
Multimodal large language models (MLLMs) have shown satisfactory effects in many autonomous driving tasks. In this paper, MLLMs are utilized to solve joint semantic scene understanding and risk localization tasks, while only relying on front-view ima
Externí odkaz:
http://arxiv.org/abs/2412.19406
Large vision-language models (LVLMs) have demonstrated remarkable capabilities in multimodal understanding and generation tasks. However, these models occasionally generate hallucinatory texts, resulting in descriptions that seem reasonable but do no
Externí odkaz:
http://arxiv.org/abs/2412.07518
Fine-tuning large language models (LLMs) with Low-Rank adaption (LoRA) is widely acknowledged as an effective approach for continual learning for new tasks. However, it often suffers from catastrophic forgetting when dealing with multiple tasks seque
Externí odkaz:
http://arxiv.org/abs/2409.19611
Autor:
Wu, Jianhua, Gao, Bingzhao, Gao, Jincheng, Yu, Jianhao, Chu, Hongqing, Yu, Qiankun, Gong, Xun, Chang, Yi, Tseng, H. Eric, Chen, Hong, Chen, Jie
With the development of artificial intelligence and breakthroughs in deep learning, large-scale Foundation Models (FMs), such as GPT, Sora, etc., have achieved remarkable results in many fields including natural language processing and computer visio
Externí odkaz:
http://arxiv.org/abs/2405.02288
Autor:
Zhu, Jiageng, Xie, Hanchen, Wu, Jianhua, Li, Jiazhi, Khayatkhoei, Mahyar, Hussein, Mohamed E., AbdAlmageed, Wael
Discovering causal relations among semantic factors is an emergent topic in representation learning. Most causal representation learning (CRL) methods are fully supervised, which is impractical due to costly labeling. To resolve this restriction, wea
Externí odkaz:
http://arxiv.org/abs/2308.05707
Accurate and fast segmentation of medical images is clinically essential, yet current research methods include convolutional neural networks with fast inference speed but difficulty in learning image contextual features, and transformer with good per
Externí odkaz:
http://arxiv.org/abs/2302.11802
Autor:
Marszalek, Milena, Hawking, Meredith K.D., Gutierrez, Ana, Firman, Nicola, Wu, Jianhua, Robson, John, Smith, Kelvin, Dostal, Isabel, Ahmed, Zaheer, Bedford, Helen, Billington, Anna, Dezateux, Carol
Publikováno v:
In Vaccine 1 January 2025 43 Part 1
Autor:
Wu, Jiani 1, 9, Wang, Yuanyuan 1, 9, Huang, Zhenhua 1, 9, Wu, Jingjing 1, Sun, Huiying 1, Zhou, Rui 1, Qiu, Wenjun 1, Ye, Zilan 4, Fang, Yiran 1, Huang, Xiatong 1, Wu, Jianhua 1, Bin, Jianping 5, Liao, Yulin 5, Shi, Min 1, Wang, Jiguang 6, 7, 8, Liao, Wangjun 1, 2, 3, ∗, Zeng, Dongqiang 1, 2, 3, 10, ∗∗
Publikováno v:
In iScience 20 December 2024 27(12)
Publikováno v:
In Applied Thermal Engineering 15 December 2024 257 Part C