Bio

My name is Ge Chunjiang. I am currently a fifth year PhD candidate in Tsinghua University. My research interest lies in Computer Vision and Multimodal Foundation Models, and the ultimate goals are towards enabling machine learning models to understand the open world, interact with the open world.

我是葛春江，目前是清华大学五年级的博士生。我兴趣是计算机视觉和多模态基础模型，最终目标是使机器学习模型可以理解开放世界，并和开放世界交互。

I am now a Ph.D candidate of Department of Automation, Tsinghua University, advised by Prof. Shiji Song and Prof. Gao huang. Before coming to Department of Automation, I received B.S. in Department of Physics, Tsinghua University. I am actively seeking postdoctoral positions and industrial opportunities.

我目前就读于清华大学自动化系。我在清华大学物理系获得数理基础科学学位。我在寻求博士后和工业界的机会。

If you’re interested in my work or personal development, feel free to contact me. I can arrange 30 minutes per week to communicate with you. You can contact me by email.

我每周可以安排30分钟的时间和同学们交流，可以给我发邮件联系。如果你有微信，可以 微信 联系。

News

• [2024/10] Awarded by National Scholarship (国家奖学金), Ministry of Education of China.
• [2024/05] I am excited to announce that our project and paper, ConvLLaVA, has been released. We employ a hierarchical backbone for High resolution understanding, which is efficient and effective. Welcome cooperation!
• [2023/06] I establish a github repo for collecting papers on foundation models. Welcome pull requests and collaboration。

Publications

Highlight

ConvLLaVA: Hierarchical Backbones as Visual Encoder for Large Multimodal Models
Chunjiang Ge, Sijie Cheng, Ziming Wang, Jiale Yuan, Yuan Gao, Jun Song, Shiji Song, Gao Huang, Bo Zheng
TL; DR: We propose to employ a five stage ConvNeXt as the visual encoder of LMM to compress visual tokens, greatly improves performance on high resolution benchmarks and efficiency.

Domain Adaptation via Prompt Learning
Chunjiang Ge, Rui Huang, Mixue Xie, Zihang Lai, Shiji Song, Shuang Li, Gao Huang.
TL; DR: We propose a novel domain adaptation method, DAPrompt, which learns a set of domain-specific prompts to avoid information loss resulted from domain alignment.

MultiModal Large Language Models (MLLM)

ConvLLaVA: Hierarchical Backbones as Visual Encoder for Large Multimodal Models
Chunjiang Ge, Sijie Cheng, Ziming Wang, Jiale Yuan, Yuan Gao, Jun Song, Shiji Song, Gao Huang, Bo Zheng
arXiv code

Llava-uhd: an lmm perceiving any aspect ratio and high-resolution images
Ruyi Xu, Yuan Yao, Zonghao Guo, Junbo Cui, Zanlin Ni, Chunjiang Ge, Tat-Seng Chua, Zhiyuan Liu, Maosong Sun, Gao Huang.
arXiv

Traditional Computer Vision

Domain Adaptation via Prompt Learning
Chunjiang Ge, Rui Huang, Mixue Xie, Zihang Lai, Shiji Song, Shuang Li, Gao Huang.
IEEE Transactions on Neural Networks and Learning Systems (TNNLS) (IF: 10.4)
arXiv code

On the Integration of Self-Attention and Convolution
Pan, Xuran, Chunjiang Ge, Rui Lu, Shiji Song, Guanfu Chen, Zeyi Huang, and Gao Huang.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2022)
arXiv Code

Cross-Modal Adapter for Text-Video Retrieval
Haojun Jiang, Jianke Zhang, Rui Huang, Chunjiang Ge, Zanlin Ni, Shiji Song, Gao Huang
Pattern Recognition (PR) (IF: 7.5)
arXiv code

Causal Intervention for Human Trajectory Prediction with Cross Attention Mechanism
Chunjiang Ge, Shiji Song and Gao Huang.
AAAI Conference on Artificial Intelligence (AAAI 2023)
paper

Large scale air pollution prediction with deep convolutional networks
Chunjiang Ge$^\ast$, Gao Huang, Tianyu Xiong, Shiji Song, Le Yang, Baoxian Liu, Wenjun Yin and Cheng Wu.
Science China Information Sciences. (IF：8.8)
Paper

Using human feedback to fine-tune diffusion models without any reward model
Kai Yang, Jian Tao, Jiafei Lyu, Chunjiang Ge, Jiaxin Chen, Weihan Shen, Xiaolong Zhu, Xiu Li.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.
Paper

Demystify Mamba in Vision: A Linear Attention Perspective
Dongchen Han, Ziyi Wang, Zhuofan Xia, Yizeng Han, Yifan Pu, Chunjiang Ge, Jun Song, Shiji Song, Bo Zheng, Gao Huang.
Paper