6 papers
Auto-FlexSwitch: Efficient Dynamic Model Merging via Learnable Task Vector Compression
Junqi Gao, Dazhi Zhang, Zhichang Guo +3
Model merging has attracted attention as an effective path toward multi-task adaptation by integrating knowledge from multiple task-specific models. Among existing approaches, dyna…
Nonlocal-to-local convergence of the -Biharmonic evolution equation with the Dirichlet boundary condition
Kehan Shi, Yi Ran
This paper studies the nonlocal -biharmonic evolution equation with the Dirichlet boundary condition that arises in image processing and data analysis. We prove the existence an…
PDAC: Efficient Coreset Selection for Continual Learning via Probability Density Awareness
Junqi Gao, Zhichang Guo, Dazhi Zhang +3
Rehearsal-based Continual Learning (CL) maintains a limited memory buffer to store replay samples for knowledge retention, making these approaches heavily reliant on the quality of…
Incorporating Local Hölder Regularity into PINNs for Solving Elliptic PDEs
Qirui Zhou, Jiebao Sun, Yi Ran +1
In this paper, local Hölder regularization is incorporated into a physics-informed neural networks (PINNs) framework for solving elliptic partial differential equations (PDEs). Mo…
Coupling local and nonlocal total variation flow for image despeckling
Yi Ran, Zhichang Guo, Kehan Shi +4
Nonlocal equations effectively preserve textures but exhibit weak regularization effects in image denoising, whereas local equations offer strong denoising capabilities yet fail to…
A Tunable Despeckling Neural Network Stabilized via Diffusion Equation
Yi Ran, Zhichang Guo, Jia Li +3
The removal of multiplicative Gamma noise is a critical research area in the application of synthetic aperture radar (SAR) imaging, where neural networks serve as a potent tool. Ho…