I am now an Associate Professor at PALM lab, Department of Computer Science, Southeast University (SEU), China. I got my B.S. degree from Nanjing University of Posts and Telecommunications (NUPT), M.S. degree from Southeast University (SEU) supervised by Prof Xin Geng, and Ph.D. from Nanyang Technological University (NTU) supervised by Prof Jianfei Cai and Prof Hanwang Zhang.
More details about me can be found in https://yxpalmweb.github.io/
I have wide interest on AI, especially machine learning and deep learning, recently, I especially focus on multi-model in-context learning and learngene framework. In the past and future few years, I will focus on the following topics:
In-Context Learning
Learngene
Large Language Model
Large Vision-Language Model
Image Captioning
Some recent published papers:
How to Configure Good In-Context Sequence for Visual Question Answering
Li Li, Jiawei Peng, Huiyi Chen, Chongyang Gao, Xu Yang
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.CVPR 2024.
ICD-LM: Configuring Vision-Language In-Context Demonstrations by Language Modeling
Yingzhe Peng, Xu Yang, Haoxuan Ma, Shuo Xu, Chi Zhang, Yucheng Han, Hanwang Zhang
Computer Vision and Pattern Recognition.arXiv.
Manipulating the Label Space for In-Context Classification
Haokun Chen, Xu Yang, Yuhang Huang, Zihan Wu, Jing Wang, Xin Geng
Computer Vision and Pattern Recognition.arXiv.
Exploring Diverse In-Context Configurations for Image Captioning
Xu Yang, Yongliang Wu, Mingzhuo Yang, Haokun Chen, Xin Geng
Annual Conference on Neural Information Processing Systems.NeurIPS2023.
Transforming Visual Scene Graphs to Image Captions
Xu Yang, Jiawei Peng, Zihua Wang, Haiyang Xu, Qinghao Ye, Chenliang Li, Ming Yan, Fei Huang, Zhangzikang Li, Yu Zhang
Association for Computational Linguistics.ACL 2023.
Learning Trajectory-Word Alignments for Video-Language Tasks
Xu Yang, Zhangzikang Li, Haiyang Xu, Hanwang Zhang, Qinghao Ye, Chenliang Li, Ming Yan, Yu Zhang, Fei Huang, Songfang Huang
International Conference on Computer Vision.ICCV 2023.
