6 papers · 1 filter
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…
Adaptive Discretization for Consistency Models
Jiayu Bai, Zhanbo Feng, Zhijie Deng +3
Consistency Models (CMs) have shown promise for efficient one-step generation. However, most existing CMs rely on manually designed discretization schemes, which can cause repeated…
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…
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…
Deep Equilibrium Models are Almost Equivalent to Not-so-deep Explicit Models for High-dimensional Gaussian Mixtures
Zenan Ling, Longbo Li, Zhanbo Feng +4
Deep equilibrium models (DEQs), as a typical implicit neural network, have demonstrated remarkable success on various tasks. There is, however, a lack of theoretical understanding…