Short Bio:
Prof. Weijiang Yu is an Associate Professor, Yat-sen Scholar in the School of Computer Science and Engineering at Sun Yat-sen University (SYSU), Guangzhou, China. Before joining SYSU, he was a researcher scientist at Huawei with the honor of Huawei Topminds and was a research intern at MSRA, Petuum, SenseTime, and Tencent. Weijiang received his Ph.D. from SYSU, advised by Prof. Nong Xiao. He is fortunate to be a visiting scholar at KAUST and CMU, where he collaborated with Prof. Bernard Ghanem and Prof. Eric P. Xing, respectively.
Join us: I am looking for self-motivated Ph.D./master students, postdoctoral reseachers, research assistants/interns, and visiting scholars, working together on exciting and cutting-edge multimodal AI, large foundation models and AI for science projects. If you are interested in working with me, please drop me an email with your resume.
Research Interests:
His research explores the bleeding edge of multimodal foundation models, reinforcement learning, computer vision, and AI for science. He has published many papers in top conferences and journals, such as TPAMI, Nature Communications, TMI, NeurIPS, CVPR, ACL, ACM Multimedia and so on. His mission is "Intelligentizing the World, Empowering Human Potential " by building generally capable agents across physical worlds and scientific worlds.
Awards:
Chinese Association for Artificial Intelligence (CAAI) Doctoral Dissertation Award, 2023 (Top 10)
ACM China Doctoral Dissertation Award Nominee, 2022 (Only three awardees among all computer disciplines across China every year)
ACM Guangzhou Doctoral Dissertation Award, 2022 (Only two awardees among all computer disciplines across South China every year)
Huawei TopMinds, 2022
Excellent Doctoral Dissertation of Sun Yat-sen University, 2022
Outstanding Graduate of Sun Yat-sen University, 2022
Stars of Tomorrow Internship Program in MSRA, 2022
National Scholarship for Doctoral Students, 2020, 2021
NeurIPS Travel Award, 2019
Guanghua Education Scholarship, 2019
The 2nd place in Key Points Detection of Apparel Track of Alibaba FashionAI Global Challenge, 2018
Telecommunications Scholarship, 2017
National Scholarship for Undergraduates, 2016
The First Prize Scholarship, 2015, 2016, 2017
The Second Prize of National Electronic Design Contest, 2015
Selected Publications:
- Weijiang Yu, Haofan Wang, Guohao Li, Nong Xiao, Bernard Ghanem.“Knowledge-aware Global Reasoning for Situation Recognition”. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2023. [CCF A] [中科院一区]
- Weijiang Yu, Haoteng Zheng, Mengfei Li, Lei Ji, Lijun Wu, Nong Xiao, Nan Duan.“Learning from Inside: Self-driven Siamese Sampling and Reasoning for Video Question Answering”. Annual Conference on Neural Information Processing Systems (NeurlPS), 2021. [CCF A]
- Weijiang Yu, Jian Liang, Lei Ji, Lu Li, Yuejian Fang, Nong Xiao, and Nan Duan . Hybrid Reasoning Network for Video-based Commonsense Captioning. ACM International Conference on Multimedia (ACM MM), 2021. [CCF A]
- Weijiang Yu, Jian Liang, Lu Li, Nong Xiao. "Single Image De-noising via Staged Memory Network". ACM International Conference on Multimedia (ACM MM), 2020 (Oral) [CCF A]
- Weijiang Yu, Jingwen Zhou, Weihao Yu, Xiaodan Liang, Nong Xiao. "Heterogeneous Graph Learning for Visual Commonsense Reasoning". Annual Conference on Neural Information Processing Systems (NeurlPS), 2019 (Spotlight) [CCF A]
- Weijiang Yu, Xiaodan Liang, Ke Gong, Chenhan Jiang, Nong Xiao. "Layout-Graph Reasoning for Fashion Landmark Detection". IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019. [CCF A]
- Weijiang Yu, Zhe Huang, Wayne Zhang, Litong Feng, Nong Xiao. "Gradual Network for Single Image De-raining". ACM International Conference on Multimedia (ACM MM), 2019 (Oral). [CCF A]
- Songyuan Yang, Weijiang Yu(通讯作者), Wenjing Yang, Xinwang Liu, Huibin Tan, Long Lan, Nong Xiao. "WildVideo: Benchmarking LMMs for Understanding Video-Language Interaction". IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2025 [CCF A][中科院一区]
- Weijiang Yu, Yingpeng Wen, Fudan Zheng, and Nong Xiao. “Improving Math Word Problems with Pre-trained Knowledge and Hierarchical Reasoning”. Conference on Empirical Methods in Natural Language Processing (EMNLP), 2021. [CCF B]
- Yuansong Zeng, Jiancong Xie, Zhuoyi Wei, Yun Su, Ningyuan Shangguan, Shuangyu Yang, Chengyang Zhang, Wenbing Li, Jinbo Zhang, Nan Fang, Hongyu Zhang, Huiying Zhao, Yutong Lu, Jue Fan, Weijiang Yu(通讯作者), Yuedong Yang. "CellFM: a large-scale foundation model pre-trained on transcriptomics of 100 million human cells". Nature Communications, 2025. [中科院一区]
- Fudan Zheng, Jindong Cao, Weijiang Yu(通讯作者), Zhiguang Chen, Nong Xiao, Yutong Lu. "Exploring Low-Resource Medical Image Classification with Weakly Supervised Prompt Learning". Pattern Recognition, 2024. [中科院一区]
- Siyao Li, Weijiang Yu, Tianpei Gu, Chunze Lin, Quan Wang, Chen Qian, Chen Change Loy, Ziwei Liu. "Bailando++: 3D Dance GPT with Choreographic Memory". IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2023. [CCF A][中科院一区]
- Congzhi Zhang, Jiawei Peng, Zhenglin Wang, Yilong Lai, Haowen Sun, Heng Chang, Fei Ma, Weijiang Yu(通讯作者). "VReST: Enhancing Reasoning in Large Vision-Language Models through Tree Search and Self-Reward Mechanism". Annual Meeting of the Association for Computational Linguistics (ACL), 2025. [CCF A]
- Siyao Li, Weijiang Yu, Tianpei Gu, Chunze Lin, Quan Wang, Chen Qian, Chen Change Loy, Ziwei Liu. "Bailando: 3D Dance Generation by Actor-Critic GPT with Choreographic Memory". IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022 (Oral). [CCF A]
Google scholar:https://scholar.google.com/citations?user=VBQPXlsAAAAJ&hl=zh-CN&oi=ao



