Faster Multi-GPU Training with PPLL: A Pipeline Parallelism Framework Leveraging Local Learning

no code implementations • 19 Nov 2024 • Xiuyuan Guo, Chengqi Xu, Guinan Guo, Feiyu Zhu, Changpeng Cai, Peizhe Wang, Xiaoming Wei, Junhao Su, Jialin Gao

To address this issue, we present PPLL (Pipeline Parallelism based on Local Learning), a novel framework that leverages local learning algorithms to enable effective parallel training across multiple GPUs.

SPEAK: Speech-Driven Pose and Emotion-Adjustable Talking Head Generation

no code implementations • 12 May 2024 • Changpeng Cai, Guinan Guo, Jiao Li, Junhao Su, Fei Shen, Chenghao He, Jing Xiao, Yuanxu Chen, Lei Dai, Feiyu Zhu

Then we design a face editing module that modifies speech content and facial latent codes into a single latent space.

Disentanglement Talking Face Generation +1

Shared and Private Information Learning in Multimodal Sentiment Analysis with Deep Modal Alignment and Self-supervised Multi-Task Learning

no code implementations • 15 May 2023 • Songning Lai, Jiakang Li, Guinan Guo, Xifeng Hu, Yulong Li, Yuan Tan, Zichen Song, Yutong Liu, Zhaoxia Ren, Chun Wan, Danmin Miao, Zhi Liu

In this work, we propose a deep modal shared information learning module based on the covariance matrix to capture the shared information between modalities.

Multimodal Sentiment Analysis Multi-Task Learning +2