Alert button
Picture for Quan Sun

Quan Sun

Alert button

EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters

Feb 06, 2024
Quan Sun, Jinsheng Wang, Qiying Yu, Yufeng Cui, Fan Zhang, Xiaosong Zhang, Xinlong Wang

Viaarxiv icon

Generative Multimodal Models are In-Context Learners

Dec 20, 2023
Quan Sun, Yufeng Cui, Xiaosong Zhang, Fan Zhang, Qiying Yu, Zhengxiong Luo, Yueze Wang, Yongming Rao, Jingjing Liu, Tiejun Huang, Xinlong Wang

Viaarxiv icon

CapsFusion: Rethinking Image-Text Data at Scale

Nov 02, 2023
Qiying Yu, Quan Sun, Xiaosong Zhang, Yufeng Cui, Fan Zhang, Yue Cao, Xinlong Wang, Jingjing Liu

Viaarxiv icon

Generative Pretraining in Multimodality

Jul 11, 2023
Quan Sun, Qiying Yu, Yufeng Cui, Fan Zhang, Xiaosong Zhang, Yueze Wang, Hongcheng Gao, Jingjing Liu, Tiejun Huang, Xinlong Wang

Figure 1 for Generative Pretraining in Multimodality
Figure 2 for Generative Pretraining in Multimodality
Figure 3 for Generative Pretraining in Multimodality
Figure 4 for Generative Pretraining in Multimodality
Viaarxiv icon

EVA-CLIP: Improved Training Techniques for CLIP at Scale

Mar 27, 2023
Quan Sun, Yuxin Fang, Ledell Wu, Xinlong Wang, Yue Cao

Figure 1 for EVA-CLIP: Improved Training Techniques for CLIP at Scale
Figure 2 for EVA-CLIP: Improved Training Techniques for CLIP at Scale
Figure 3 for EVA-CLIP: Improved Training Techniques for CLIP at Scale
Figure 4 for EVA-CLIP: Improved Training Techniques for CLIP at Scale
Viaarxiv icon

EVA-02: A Visual Representation for Neon Genesis

Mar 22, 2023
Yuxin Fang, Quan Sun, Xinggang Wang, Tiejun Huang, Xinlong Wang, Yue Cao

Figure 1 for EVA-02: A Visual Representation for Neon Genesis
Figure 2 for EVA-02: A Visual Representation for Neon Genesis
Figure 3 for EVA-02: A Visual Representation for Neon Genesis
Figure 4 for EVA-02: A Visual Representation for Neon Genesis
Viaarxiv icon

EVA: Exploring the Limits of Masked Visual Representation Learning at Scale

Nov 14, 2022
Yuxin Fang, Wen Wang, Binhui Xie, Quan Sun, Ledell Wu, Xinggang Wang, Tiejun Huang, Xinlong Wang, Yue Cao

Figure 1 for EVA: Exploring the Limits of Masked Visual Representation Learning at Scale
Figure 2 for EVA: Exploring the Limits of Masked Visual Representation Learning at Scale
Figure 3 for EVA: Exploring the Limits of Masked Visual Representation Learning at Scale
Figure 4 for EVA: Exploring the Limits of Masked Visual Representation Learning at Scale
Viaarxiv icon

Thermal Infrared Image Inpainting via Edge-Aware Guidance

Oct 28, 2022
Zeyu Wang, Haibin Shen, Changyou Men, Quan Sun, Kejie Huang

Figure 1 for Thermal Infrared Image Inpainting via Edge-Aware Guidance
Figure 2 for Thermal Infrared Image Inpainting via Edge-Aware Guidance
Figure 3 for Thermal Infrared Image Inpainting via Edge-Aware Guidance
Figure 4 for Thermal Infrared Image Inpainting via Edge-Aware Guidance
Viaarxiv icon