I am now working as a AI research scientist at Meta, focusing on image and video generative models. Previously, I was a Ph.D. student at the Institute for Information Processing at Leibniz University Hanover, working on scene understanding and generative models. I was advised by Prof. Bodo Rosenhahn and Prof. Michael Ying Yang.
My research interest lies in computer vision and graphics:
Please feel free to contact me by email for any questions or collaboration!
@misc{chen2023gentron,
title={GenTron: Delving Deep into Diffusion Transformers for Image and Video Generation},
author={Shoufa Chen and Mengmeng Xu and Jiawei Ren and Yuren Cong and Sen He and Yanping Xie and Animesh Sinha and Ping Luo and Tao Xiang and Juan-Manuel Perez-Rua},
year={2023},
eprint={2312.04557},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
@article{cong2023flatten,
title={FLATTEN: optical FLow-guided ATTENtion for consistent text-to-video editing},
author={Cong, Yuren and Xu, Mengmeng and Simon, Christian and Chen, Shoufa and Ren, Jiawei and Xie, Yanping and Perez-Rua, Juan-Manuel and Rosenhahn, Bodo and Xiang, Tao and He, Sen},
journal={arXiv preprint arXiv:2310.05922},
year={2023}
}
@article{cong2023learning,
title={Learning Similarity between Scene Graphs and Images with Transformers},
author={Cong, Yuren and Liao, Wentong and Rosenhahn, Bodo and Yang, Michael Ying},
journal={arXiv preprint arXiv:2304.00590},
year={2023}
}
@InProceedings{Cong_2023_CVPR,
author = {Cong, Yuren and Yi, Jinhui and Rosenhahn, Bodo and Yang, Michael Ying},
title = {SSGVS: Semantic Scene Graph-to-Video Synthesis},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2023},
pages = {2555-2565}
}
@article{cong2023reltr,
title={Reltr: Relation transformer for scene graph generation},
author={Cong, Yuren and Yang, Michael Ying and Rosenhahn, Bodo},
journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
year={2023},
publisher={IEEE}
}
@article{cong2023attribute,
title={Attribute-centric compositional text-to-image generation},
author={Cong, Yuren and Min, Martin Renqiang and Li, Li Erran and Rosenhahn, Bodo and Yang, Michael Ying},
journal={arXiv preprint arXiv:2301.01413},
year={2023}
}
@InProceedings{Cong_2021_ICCV,
author = {Cong, Yuren and Liao, Wentong and Ackermann, Hanno and Rosenhahn, Bodo and Yang, Michael Ying},
title = {Spatial-Temporal Transformer for Dynamic Scene Graph Generation},
booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
month = {October},
year = {2021},
pages = {16372-16382}
}
@InProceedings{cong2020nodis,
title={Nodis: Neural ordinary differential scene understanding},
author={Cong, Yuren and Ackermann, Hanno and Liao, Wentong and Yang, Michael Ying and Rosenhahn, Bodo},
booktitle={Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part XX 16},
pages={636--653},
year={2020},
organization={Springer}
}