Alert button
Picture for Yufeng Cui

Yufeng Cui

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

Fast-BEV: A Fast and Strong Bird's-Eye View Perception Baseline

Jan 29, 2023
Yangguang Li, Bin Huang, Zeren Chen, Yufeng Cui, Feng Liang, Mingzhu Shen, Fenggang Liu, Enze Xie, Lu Sheng, Wanli Ouyang, Jing Shao

Figure 1 for Fast-BEV: A Fast and Strong Bird's-Eye View Perception Baseline
Figure 2 for Fast-BEV: A Fast and Strong Bird's-Eye View Perception Baseline
Figure 3 for Fast-BEV: A Fast and Strong Bird's-Eye View Perception Baseline
Figure 4 for Fast-BEV: A Fast and Strong Bird's-Eye View Perception Baseline
Viaarxiv icon

Democratizing Contrastive Language-Image Pre-training: A CLIP Benchmark of Data, Model, and Supervision

Mar 11, 2022
Yufeng Cui, Lichen Zhao, Feng Liang, Yangguang Li, Jing Shao

Figure 1 for Democratizing Contrastive Language-Image Pre-training: A CLIP Benchmark of Data, Model, and Supervision
Figure 2 for Democratizing Contrastive Language-Image Pre-training: A CLIP Benchmark of Data, Model, and Supervision
Figure 3 for Democratizing Contrastive Language-Image Pre-training: A CLIP Benchmark of Data, Model, and Supervision
Figure 4 for Democratizing Contrastive Language-Image Pre-training: A CLIP Benchmark of Data, Model, and Supervision
Viaarxiv icon

Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm

Oct 11, 2021
Yangguang Li, Feng Liang, Lichen Zhao, Yufeng Cui, Wanli Ouyang, Jing Shao, Fengwei Yu, Junjie Yan

Figure 1 for Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm
Figure 2 for Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm
Figure 3 for Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm
Figure 4 for Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm
Viaarxiv icon