My name is Jinguo Zhu (祝金国), now is a young researcher at the Shanghai AI Laboratory, China. My research interest focuses on the pre-training and post-training for large multimodal models.

I got my Ph.D. degree from the Xi’an Jiaotong University in 2024, supervised by Prof. Mingzhe Rong and Prof. Xiaohua Wang. Before that, I received my B.S. degree from the Xi’an Jiaotong University in 2019.

🔥 News

• 2024.12:  🎉🎉 Our team released InternVL-2.5.
• 2024.07:  🎉🎉 Our team released InternVL-2.0.
• 2024.05: Our vision model pre-training method Latent Compression Learning (LCL) was accepted by NeurIPS 2024.

📝 Publications

CVPR 2022

Uni-Perceiver: Pre-training unified architecture for generic perception for zero-shot and few-shot tasks

Xizhou Zhu, Jinguo Zhu, Hao Li, Xiaoshi Wu, Hongsheng Li, Xiaohua Wang, Jifeng Dai

Project

• Uni-Perceiver is a generalist model for vision and language tasks.

• CVPR 2023 Uni-Perceiver v2: A Generalist Model for Large-Scale Vision and Vision-Language Tasks., Hao Li, Jinguo Zhu, Xiaohu Jiang, Xizhou Zhu, Hongsheng Li, Chun Yuan, Xiaohua Wang, Yu Qiao, Xiaogang Wang, Wenhai Wang, Jifeng Dai.
• NeurIPS 2022 Uni-Perceiver-MoE: Learning sparse generalist models with conditional moes, Jinguo Zhu, Xizhou Zhu, Wenhai Wang, Xiaohua Wang, Hongsheng Li, Xiaogang Wang, Jifeng Dai.
• CVPR 2021 Complementary Relation Contrastive Distillation, Jinguo Zhu, Shixiang Tang, Dapeng Chen, et al.

🎖 Honors and Awards

• 2018.07 National First Prize in National Undergraduate Electronic Design Contest.
• 2017.07 National First Prize in National Undergraduate Robot Contest (ABU Robocon).
• 2016.12 National First Prize in Mathematics competition of Chinese College Students.

📖 Educations

• 2019.06 - 2024.09, Ph.D., Xi’an Jiaotong University, China.
• 2015.09 - 2019.06, Undergraduate, Xi’an Jiaotong University, China.

💻 Internships

• 2023.06 - 2024.05, AI Lab, Tencent.
• 2021.02 - 2023.05, SenseTime Research & Shanghai AI Laboratory.
• 2020.06 - 2021.02, SCG, SenseTime.