Zobrazeno 1 - 10
of 248
pro vyhledávání: '"Gao, Ziqi"'
Non-semantic context information is crucial for visual recognition, as the human visual perception system first uses global statistics to process scenes rapidly before identifying specific objects. However, while semantic information is increasingly
Externí odkaz:
http://arxiv.org/abs/2410.23577
Low-Rank Adaptation (LoRA) has gained popularity for fine-tuning large foundation models, leveraging low-rank matrices $\mathbf{A}$ and $\mathbf{B}$ to represent weight changes (i.e., $\Delta \mathbf{W} = \mathbf{B} \mathbf{A}$). This method reduces
Externí odkaz:
http://arxiv.org/abs/2407.19342
Low-rank adaptation~(LoRA) has recently gained much interest in fine-tuning foundation models. It effectively reduces the number of trainable parameters by incorporating low-rank matrices $A$ and $B$ to represent the weight change, i.e., $\Delta W=BA
Externí odkaz:
http://arxiv.org/abs/2405.03003
AlphaFold can be used for both single-chain and multi-chain protein structure prediction, while the latter becomes extremely challenging as the number of chains increases. In this work, by taking each chain as a node and assembly actions as edges, we
Externí odkaz:
http://arxiv.org/abs/2405.02299
Multi-contrast (MC) Magnetic Resonance Imaging (MRI) reconstruction aims to incorporate a reference image of auxiliary modality to guide the reconstruction process of the target modality. Known MC reconstruction methods perform well with a fully samp
Externí odkaz:
http://arxiv.org/abs/2403.05256
Understanding the 3D structures of protein multimers is crucial, as they play a vital role in regulating various cellular processes. It has been empirically confirmed that the multimer structure prediction~(MSP) can be well handled in a step-wise ass
Externí odkaz:
http://arxiv.org/abs/2402.18813
Autor:
Gao, Ziqi, Zhou, S. Kevin
Implicit visual knowledge in a large latent diffusion model (LLDM) pre-trained on natural images is rich and hypothetically universal to natural and medical images. To test this hypothesis from a practical perspective, we propose a novel framework fo
Externí odkaz:
http://arxiv.org/abs/2402.10609
Autor:
Gao, Ziqi
Molecular dynamics (MD) simulations play a pivotal role in understanding the behavior of complex molecular systems, offering insights into the behavior of molecules at the atomic level, while their accuracy heavily depends on the force field paramete
Externí odkaz:
http://hdl.handle.net/11375/29200
With a long history of traditional Graph Anomaly Detection (GAD) algorithms and recently popular Graph Neural Networks (GNNs), it is still not clear (1) how they perform under a standard comprehensive setting, (2) whether GNNs can outperform traditio
Externí odkaz:
http://arxiv.org/abs/2306.12251
Autor:
Gao, Ziqi, Zhou, S. Kevin
Undersampled MRI reconstruction is crucial for accelerating clinical scanning. Dual-domain reconstruction network is performant among SoTA deep learning methods. In this paper, we rethink dual-domain model design from the perspective of the receptive
Externí odkaz:
http://arxiv.org/abs/2303.10611