“只问是非，不计利害”
"Seek only truth, indifferent to profit or loss."
                        ——  竺可桢  (Chu Kochen)
        

About Me

In Jul 2025, I will join Manycore Tech Inc. as a research scientist in Prof. Zihan Zhou’s team.

I received my Ph.D. degree at Zhejiang University under the supervision of Prof. Jun Xiao (Sep 2020 - June 2025). I visited at The Hong Kong University of Science and Technology (as a visiting Ph.D. student) under the supervision of Prof. Long Chen (Sep 2024 - Feb 2025). I visited Nanyang Technological University and Singapore Management University (as a visiting Ph.D. setudent), under the supervision of Prof. Hanwang Zhang and Prof. Qianru Sun (Sep 2022 - Sep 2023). I got my B.E. degree in Ocean engineering at Zhejiang University (Sep 2016 - Jun 2020).

Recent co-author: Dr. Jiaxin Shi

My research interests mainly include Computer Vision, Multimodal Analysis, and Video Generation and Editing.

Publications

— [!NEW] —

• Kaifeng Gao, Jiaxin Shi, Hanwang Zhang, Chunping Wang, Jun Xiao, Long Chen. Ca2-VDM: Efficient Autoregressive Video Diffusion Model with Causal Generation and Cache Sharing. In International Conference on Machine Learning (ICML) 2025. [arXiv][Code]

• Kaifeng Gao, Siqi Chen, Hanwang Zhang, Jun Xiao, Yueting Zhuang, and Qianru Sun, Generalized Visual Relation Detection with Diffusion Models. Accepted to be published on IEEE Transactions on Circuits and Systems for Video Technology (TCSVT) 2025.

• Wenqing Wang, Kaifeng Gao, Yawei Luo, Tao Jiang, Fei Gao, Jian Shao, Jianwen Sun, Jun Xiao. Triple Correlations-Guided Label Supplementation for Unbiased Video Scene Graph Generation. In Proceedings of the 31st ACM International Conference on Multimedia (ACM MM), 2023. [Paper][arXiv]

• Kaifeng Gao, Long Chen, Hanwang Zhang, Jun Xiao, Qianru Sun. Compositional Prompt Tuning with Motion Cues for Open-vocabulary Video Relation Detection. In International Conference on Learning Representations (ICLR), 2023. [Paper][Code]

• Kaifeng Gao, Long Chen, Yulei Niu, Jian Shao, and Jun Xiao. Classification-Then-Grounding: Reformulating Video Scene Graphs as Temporal Bipartite Graphs, In Proceedings of the IEEE conference on Computer Vision and Pattern Recognition (CVPR), 2022. [Paper][Code]

• Shaoning Xiao, Long Chen, Kaifeng Gao, Zhao Wang, Yi Yang, Jun Xiao. Rethinking Multi-Modal Alignment in Video Question Answering from Feature and Sample Perspectives. In The 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2022. [Paper]

• Kaifeng Gao, Long Chen, Yifeng Huang, and Jun Xiao. Video Relation Detection via Tracklet based Visual Transformer. In Proceedings of the 29th ACM International Conference on Multimedia (ACM MM), 2021. [Paper][arXiv][Code]