1 code implementation • 13 Oct 2023 • Xiangyu Zhao, Bo Liu, Qijiong Liu, Guangyuan Shi, Xiao-Ming Wu
We present EasyGen, an efficient model designed to enhance multimodal understanding and generation by harnessing the capabilities of diffusion models and large language models (LLMs).
1 code implementation • 22 Feb 2023 • Guangyuan Shi, Qimai Li, Wenlong Zhang, Jiaxin Chen, Xiao-Ming Wu
Our experiments show that such a simple approach can greatly reduce the occurrence of conflicting gradients in the remaining shared layers and achieve better performance, with only a slight increase in model parameters in many cases.
no code implementations • 10 May 2022 • Wenlong Zhang, Guangyuan Shi, Yihao Liu, Chao Dong, Xiao-Ming Wu
The recently proposed practical degradation model includes a full spectrum of degradation types, but only considers complex cases that use all degradation types in the degradation process, while ignoring many important corner cases that are common in the real world.
1 code implementation • NeurIPS 2021 • Guangyuan Shi, Jiaxin Chen, Wenlong Zhang, Li-Ming Zhan, Xiao-Ming Wu
Our study shows that existing methods severely suffer from catastrophic forgetting, a well-known problem in incremental learning, which is aggravated due to data scarcity and imbalance in the few-shot setting.
Ranked #7 on Few-Shot Class-Incremental Learning on mini-Imagenet
no code implementations • Findings (EMNLP) 2021 • Haode Zhang, Yuwei Zhang, Li-Ming Zhan, Jiaxin Chen, Guangyuan Shi, Xiao-Ming Wu, Albert Y. S. Lam
This paper investigates the effectiveness of pre-training for few-shot intent classification.