7 papers
Consistency Deep Equilibrium Models
Junchao Lin, Zenan Ling, Jingwen Xu +1
Deep Equilibrium Models (DEQs) have emerged as a powerful paradigm in deep learning, offering the ability to model infinite-depth networks with constant memory usage. However, DEQs…
Diving into Kronecker Adapters: Component Design Matters
Jiayu Bai, Danchen Yu, Zhenyu Liao +4
Kronecker adapters have emerged as a promising approach for fine-tuning large-scale models, enabling high-rank updates through tunable component structures. However, existing work…
IGNN-Solver: A Graph Neural Solver for Implicit Graph Neural Networks
Junchao Lin, Zenan Ling, Zhanbo Feng +6
Implicit graph neural networks (IGNNs), which exhibit strong expressive power with a single layer, have recently demonstrated remarkable performance in capturing long-range depende…
Textual and Visual Prompt Fusion for Image Editing via Step-Wise Alignment
Zhanbo Feng, Zenan Ling, Xinyu Lu +6
The use of denoising diffusion models is becoming increasingly popular in the field of image editing. However, current approaches often rely on either image-guided methods, which p…
Nonstationary Sparse Spectral Permanental Process
Zicheng Sun, Yixuan Zhang, Zenan Ling +2
Existing permanental processes often impose constraints on kernel types or stationarity, limiting the model's expressiveness. To overcome these limitations, we propose a novel appr…
Series-to-Series Diffusion Bridge Model
Hao Yang, Zhanbo Feng, Feng Zhou +2
Diffusion models have risen to prominence in time series forecasting, showcasing their robust capability to model complex data distributions. However, their effectiveness in determ…