Kaiyuan Gao (高开元)  Ph.D. Student Huazhong University of Science and Technology Joint Ph.D. at Microsoft Research AI4Science Email: im_kai[AT]hust[DOT]edu.cn [Google Scholar] [CV]

Biography

I am a final-year Ph.D. Candidate in a joint program between Huazhong University of Science and Technology and Microsoft Research Asia, advised by Prof. Kun He and Dr. Tie-Yan Liu. Previously, I received my B.S. degree from the Department of Aritificial Intelligence and Automation of Huazhong University of Science and Technology in July 2021.

During my time at Microsoft Research, I worked on 3D molecular structure modeling and molecule generation using diffusion and language models, with in-depth research on molecular docking. Currently, I am a core contributor to the Qwen-Image project, where I actively contribute to research on image editing and the development of visual generation within the Qwen team.

Looking for industrial research positions. Expect to graduate in June 2026. Drop me an email if you feel interested.

Selected Publications

Visual Generation:

• Qwen-Image Technical Report
  Chenfei Wu, Jiahao Li, Jingren Zhou, Junyang Lin, Kaiyuan Gao, Kun Yan, Sheng-ming Yin, Shuai Bai, Xiao Xu, Yilei Chen, Yuxiang Chen, Zecheng Tang, Zekai Zhang, Zhengyi Wang, An Yang, Bowen Yu, Chen Cheng, Dayiheng Liu, Deqing Li, Hang Zhang, Hao Meng, Hu Wei, Jingyuan Ni, Kai Chen, Kuan Cao, Liang Peng, Lin Qu, Minggang Wu, Peng Wang, Shuting Yu, Tingkun Wen, Wensen Feng, Xiaoxiao Xu, Yi Wang, Yichang Zhang, Yongqiang Zhu, Yujia Wu, Yuxuan Cai, Zenan Liu
  [Code: 4.2k Stars] [Text-to-Image Model: 144k Downloads] [Image Edit Model: 28k Downloads]

3D Molecular Structure Modeling:

• Fabind: Fast and accurate protein-ligand binding
  Qizhi Pei*, Kaiyuan Gao*, Lijun Wu, Jinhua Zhu, Yingce Xia, Shufang Xie, Tao Qin, Kun He, Tie-Yan Liu, Rui Yan
  Advances in Neural Information Processing Systems (NeurIPS 2023)
  [Code: 134 Stars] [Weights]
• FABind+: Enhancing Molecular Docking through Improved Pocket Prediction and Pose Generation
  Kaiyuan Gao, Qizhi Pei, Gongbo Zhang, Jinhua Zhu, Kun He, Lijun Wu
  ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2025)
  [Code: 134 Stars] [Weights]
• Fast and Accurate Blind Flexible Docking
  Zizhuo Zhang, Lijun Wu, Kaiyuan Gao, Jiangchao Yao, Tao Qin, Bo Han
  International Conference on Learning Representations (ICLR 2025)
  [Code: 134 Stars] [Weights]
• Pre-training antibody language models for antigen-specific computational antibody design
  Kaiyuan Gao, Lijun Wu, Jinhua Zhu, Tianbo Peng, Yingce Xia, Liang He, Shufang Xie, Tao Qin, Haiguang Liu, Kun He, Tie-Yan Liu
  ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2023)
  [Code: 53 Stars] [Weights]
• CovDocker: Benchmarking Covalent Drug Design with Tasks, Datasets, and Solutions
  Yangzhe* Peng, Kaiyuan Gao*, Liang He, Yuheng Cong, Haiguang Liu, Kun He, Lijun Wu
  ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2025)
  [Code] [Datasets]

Multimodal Molecular Learning:

• Tokenizing 3d molecule structure with quantized spherical coordinates
  Kaiyuan Gao, Yusong Wang, Haoxiang Guan, Zun Wang, Qizhi Pei, John E Hopcroft, Kun He, Lijun Wu
  
• 3D-MolT5: Towards Unified 3D Molecule-Text Modeling with 3D Molecular Tokenization
  Qizhi Pei, Lijun Wu, Kaiyuan Gao, Jinhua Zhu, Rui Yan
  International Conference on Learning Representations (ICLR 2025)
• Biot5: Enriching cross-modal integration in biology with chemical knowledge and natural language associations
  Qizhi Pei, Wei Zhang, Jinhua Zhu, Kehan Wu, Kaiyuan Gao, Lijun Wu, Yingce Xia, Rui Yan
  Empirical Methods in Natural Language Processing 2023 (EMNLP 2023)
  [Code: 118 Stars] [Weights]
• Biot5+: Towards generalized biological understanding with iupac integration and multi-task tuning
  Qizhi Pei, Lijun Wu, Kaiyuan Gao, Xiaozhuan Liang, Yin Fang, Jinhua Zhu, Shufang Xie, Tao Qin, Rui Yan
  The Association for Computational Linguistics (ACL 2024 (Findings))
  [Code: 118 Stars] [Weights]
• Naturelm: Deciphering the language of nature for scientific discovery
  Yingce Xia, Peiran Jin, Shufang Xie, Liang He, Chuan Cao, Renqian Luo, Guoqing Liu, Yue Wang, Zequn Liu, Yuan-Jyue Chen, Zekun Guo, Yeqi Bai, Pan Deng, Yaosen Min, Ziheng Lu, Hongxia Hao, Han Yang, Jielan Li, Chang Liu, Jia Zhang, Jianwei Zhu, Kehan Wu, Wei Zhang, Kaiyuan Gao, Qizhi Pei, Qian Wang, Xixian Liu, Yanting Li, Houtian Zhu, Yeqing Lu, Mingqian Ma, Zun Wang, Tian Xie, Krzysztof Maziarz, Marwin Segler, Zhao Yang, Zilong Chen, Yu Shi, Shuxin Zheng, Lijun Wu, Chen Hu, Peggy Dai, Tie-Yan Liu, Haiguang Liu, Tao Qin
  [Project Page] [Code] [Weights]

Graph Learning:

• NAGphormer: A tokenized graph transformer for node classification in large graphs
  Jinsong Chen*, Kaiyuan Gao*, Gaichao Li, Kun He
  International Conference on Learning Representations (ICLR 2022)
  [Code: 129 Stars]
• Nagphormer+: A tokenized graph transformer with neighborhood augmentation for node classification in large graphs
  Jinsong Chen*, Kaiyuan Gao*, Gaichao Li, Kun He
  IEEE Transactions on Big Data (TBD)

* indicates co-first authors.