Zobrazeno 1 - 10
of 872
pro vyhledávání: '"Zhang Yiyuan"'
Publikováno v:
Open Medicine, Vol 18, Iss 1, Pp 709-33 (2023)
To explore the pharmacological mechanism of naringin (NRG) in renal fibrosis (RF) based on network pharmacology combined with molecular docking and experimental validation. We used databases to screen for the targets of NRG and RF. The “drug-diseas
Externí odkaz:
https://doaj.org/article/4370ad76320a41788a3de7083af93f01
Search engines enable the retrieval of unknown information with texts. However, traditional methods fall short when it comes to understanding unfamiliar visual content, such as identifying an object that the model has never seen before. This challeng
Externí odkaz:
http://arxiv.org/abs/2410.21220
Autor:
Zhang, Bobing, Zhang, Yiyuan, Li, Yiming, Xuan, Sicheng, Ng, Hong Wei, Liufu, Yuliang, Tang, Zhiqiang, Laschi, Cecilia
Underwater vehicles have seen significant development over the past seventy years. However, bio-inspired propulsion robots are still in their early stages and require greater interdisciplinary collaboration between biologists and roboticists. The oct
Externí odkaz:
http://arxiv.org/abs/2410.11764
This paper proposes the paradigm of large convolutional kernels in designing modern Convolutional Neural Networks (ConvNets). We establish that employing a few large kernels, instead of stacking multiple smaller ones, can be a superior design strateg
Externí odkaz:
http://arxiv.org/abs/2410.08049
We propose to build omni-modal intelligence, which is capable of understanding any modality and learning universal representations. In specific, we propose a scalable pretraining paradigm, named Multimodal Context (MiCo), which can scale up the numbe
Externí odkaz:
http://arxiv.org/abs/2406.09412
We introduce $\textit{InteractiveVideo}$, a user-centric framework for video generation. Different from traditional generative approaches that operate based on user-provided images or text, our framework is designed for dynamic interaction, allowing
Externí odkaz:
http://arxiv.org/abs/2402.03040
We propose to improve transformers of a specific modality with irrelevant data from other modalities, e.g., improve an ImageNet model with audio or point cloud datasets. We would like to highlight that the data samples of the target modality are irre
Externí odkaz:
http://arxiv.org/abs/2401.14405
Autor:
Ding, Lihe, Dong, Shaocong, Huang, Zhanpeng, Wang, Zibin, Zhang, Yiyuan, Gong, Kaixiong, Xu, Dan, Xue, Tianfan
Most 3D generation research focuses on up-projecting 2D foundation models into the 3D space, either by minimizing 2D Score Distillation Sampling (SDS) loss or fine-tuning on multi-view datasets. Without explicit 3D priors, these methods often lead to
Externí odkaz:
http://arxiv.org/abs/2312.04963
Autor:
Han, Jiaming, Gong, Kaixiong, Zhang, Yiyuan, Wang, Jiaqi, Zhang, Kaipeng, Lin, Dahua, Qiao, Yu, Gao, Peng, Yue, Xiangyu
Multimodal large language models (MLLMs) have gained significant attention due to their strong multimodal understanding capability. However, existing works rely heavily on modality-specific encoders, which usually differ in architecture and are limit
Externí odkaz:
http://arxiv.org/abs/2312.03700
The construction of online vectorized High-Definition (HD) maps is critical for downstream prediction and planning. Recent efforts have built strong baselines for this task, however, shapes and relations of instances in urban road systems are still u
Externí odkaz:
http://arxiv.org/abs/2312.03341