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…
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…
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…
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…