DeeDiff: Dynamic Uncertainty-Aware Early Exiting for Accelerating Diffusion Model Generation

no code implementations • 29 Sep 2023 • Shengkun Tang, Yaqing Wang, Caiwen Ding, Yi Liang, Yao Li, Dongkuan Xu

In this work, we propose DeeDiff, an early exiting framework that adaptively allocates computation resources in each sampling step to improve the generation efficiency of diffusion models.

text-guided-generation

You Need Multiple Exiting: Dynamic Early Exiting for Accelerating Unified Vision Language Model

1 code implementation • CVPR 2023 • Shengkun Tang, Yaqing Wang, Zhenglun Kong, Tianchi Zhang, Yao Li, Caiwen Ding, Yanzhi Wang, Yi Liang, Dongkuan Xu

To handle this challenge, we propose a novel early exiting strategy for unified visual language models, which allows dynamically skip the layers in encoder and decoder simultaneously in term of input layer-wise similarities with multiple times of early exiting, namely \textbf{MuE}.

Language Modelling

DDR-Net: Learning Multi-Stage Multi-View Stereo With Dynamic Depth Range

2 code implementations • 26 Mar 2021 • Puyuan Yi, Shengkun Tang, Jian Yao

Distinct from these approaches, we propose a Dynamic Depth Range Network (DDR-Net) to determine the depth range hypotheses dynamically by applying a range estimation module (REM) to learn the uncertainties of range hypotheses in the former stages.