Search Results for author: Junqin Huang

Found 3 papers, 0 papers with code

Piccolo2: General Text Embedding with Multi-task Hybrid Loss Training

no code implementations11 May 2024 Junqin Huang, Zhongjie Hu, Zihao Jing, Mengya Gao, Yichao Wu

In this report, we introduce Piccolo2, an embedding model that surpasses other models in the comprehensive evaluation over 6 tasks on CMTEB benchmark, setting a new state-of-the-art.

GLaMa: Joint Spatial and Frequency Loss for General Image Inpainting

no code implementations15 May 2022 Zeyu Lu, Junjun Jiang, Junqin Huang, Gang Wu, Xianming Liu

Our proposed GLaMa can better capture different types of missing information by using more types of masks.

Image Inpainting SSIM

One to Transfer All: A Universal Transfer Framework for Vision Foundation Model with Few Data

no code implementations24 Nov 2021 Yujie Wang, Junqin Huang, Mengya Gao, Yichao Wu, Zhenfei Yin, Ding Liang, Junjie Yan

Transferring with few data in a general way to thousands of downstream tasks is becoming a trend of the foundation model's application.

Cannot find the paper you are looking for? You can Submit a new open access paper.