深圳理工大学人工智能研究院特聘正教授。研究聚焦于计算机视觉和多模态大语言模型方向，在各类顶级会议及期刊发表论文36篇，成果发表于IEEE conference on computer vision and pattern recognition(CVPR)、IEEE International Conference on Computer Vision(ICCV)、European Conference on Computer Vision(ECCV) 和IEEE transactions on pattern analysis and machine intelligence(TPAMI)等知名期刊会议，学术引用量4k+，h-index 22。曾多次担任 CVPR、ICCV等国际顶级会议及期刊审稿人。

产业合作经验丰富，曾于商汤科技顶级人工智能企业担任高级算法总监兼行业算法研发团队负责人，曾负责过自动驾驶物体感知模块研发、智慧城市行业视觉感知模块研发和金融行业大模型落地应用算法研发，已获得/审查中的各类专利上百个。

学历：

2007年9月至2011年7月，中国科学技术大学，电子信息工程，学士；

2007年9月至2011年7月，中国科学技术大学，金融工程，学士（双学位）；

2012年8月至2016年7月，香港中文大学，电子工程，博士。

工作经历：

2011年11月至2012年7月，香港中文大学，研究助理职位；

2016年8月至2025年7月，商汤科技公司，高级算法总监职位；

2025年7月至今，深圳理工大学，特聘正教授职位。

所获荣誉：

2016年深圳高层次人才

2015年Google Global PhD Fellowship(1/8亚洲、1/44全球)

2014-2016多届ImageNet图像/视频物体识别比赛冠亚军

计算机视觉、多模态大模型

科研成果:

1.Chengqi Duan, Rongyao Fang, Yuqing Wang, Kun Wang, Linjiang Huang, Xingyu Zeng, Hongsheng Li, XihuiLiu.”GoT-R1: Unleashing Reasoning Capability of MLLM for Visual Generation with Reinforcement Learning.”arXiv preprint arXiv:2505.17022 (2025).

2.Yize Zhang, Tianshu Wang, Sirui Chen, Kun Wang, Xingyu Zeng, Hongyu Lin, Xianpei Han, Le Sun, ChaochaoLu.”ARise: Towards Knowledge-Augmented Reasoning via Risk-Adaptive Search.”arXiv preprint arXiv:2504.10893(2025).

3.Rongyao Fang, Chengqi Duan, Kun Wang, Linjiang Huang, Hao Li, Shilin Yan, Hao Tian, Xingyu Zeng,Rui Zhao, Jifeng Dai, Xihui Liu, Hongsheng Li.”Got: Unleashing reasoning capability of multimodal largelanguage model for visual generation and editing.”arXiv preprint arXiv:2503.10639 (2025).

4.Yilun Kong, Jingqing Ruan, Yihong Chen, Bin Zhang, Tianpeng Bao, Shi Shiwei, Du Qing, Xiaoru Hu,Hangyu Mao, Ziyue Li, Xingyu Zeng, Rui Zhao, Xueqian Wang.”TPTU-v2: Boosting Task Planning andTool Usage of Large Language Model-based Agents in Real-world Industry Systems.”Proceedings of the 2024Conference on Empirical Methods in Natural Language Processing: Industry Track. 2024.

5.Rongyao Fang, Chengqi Duan, Kun Wang, Hao Li, Hao Tian, Xingyu Zeng, Rui Zhao, Jifeng Dai, HongshengLi, Xihui Liu.”Puma: Empowering unified mllm with multi-granular visual generation.”arXiv preprintarXiv:2410.13861 (2024).

6.Chenyang Zhao, Kun Wang, Xingyu Zeng, Rui Zhao, Antoni B Chan.”Gradient-based Visual Explanation forTransformer-based CLIP.”International Conference on Machine Learning. PMLR, 2024.

7.Sirui Chen, Mengying Xu, Kun Wang, Xingyu Zeng, Rui Zhao, Shengjie Zhao, Chaochao Lu.”CLEAR:Can Language Models Really Understand Causal Graphs?.”In Findings of the Association for ComputationalLinguistics: EMNLP 2024

8.Sirui Chen, Bo Peng, Meiqi Chen, Ruiqi Wang, Mengying Xu, Xingyu Zeng, Rui Zhao, Shengjie Zhao, YuQiao, Chaochao Lu.”Causal Evaluation of Language Models.”arXiv preprint arXiv:2405.00622 (2024).

9.Yilun Kong, Jingqing Ruan, Yihong Chen, Bin Zhang, Tianpeng Bao, Shiwei Shi, Guoqing Du, Xiaoru Hu,Hangyu Mao, Ziyue Li, Xingyu Zeng, Rui Zhao.”Tptu: Task planning and tool usage of large languagemodel-based ai agents.”NeurIPS 2023 Foundation Models for Decision Making Workshop. 2023.

10.Yuhan Sun, Mukai Li, Yixin Cao, Kun Wang, Wenxiao Wang, Xingyu Zeng, Rui Zhao.”To be or not to be?an exploration of continuously controllable prompt engineering.”arXiv preprint arXiv:2311.09773 (2023).

11.Zhixuan Liang, Xingyu Zeng, Rui Zhao, Ping Luo.”MeanAP-Guided Reinforced Active Learning for ObjectDetection.”arXiv preprint arXiv:2310.08387 (2023).

12.Guoqiang Jin, Fan Yang, Mingshan Sun, Ruyi Zhao, Yakun Liu, Wei Li, Tianpeng Bao, Liwei Wu, Xingyu Zeng,Rui Zhao.”SeqCo-DETR: Sequence Consistency Training for Self-supervised Object Detection with Transformers.”BMVC 2023.

13.Shaobo Lin, Xingyu Zeng, Rui Zhao.”Explore the Power of Dropout on Few-shot Learning.”arXiv preprintarXiv:2301.11015 (2023).

14.Shaobo Lin, Kun Wang, Xingyu Zeng, Rui Zhao.”Explore the power of synthetic data on few-shot objectdetection.”Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2023.

15.Shaobo Lin, Kun Wang, Xingyu Zeng, Rui Zhao.”An effective crop-paste pipeline for few-shot object detection.”Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2023.

16.Guoqiu Li, Guanxiong Cai, Xingyu Zeng, Rui Zhao.”Scale-aware spatio-temporal relation learning for videoanomaly detection.”European Conference on Computer Vision. Cham: Springer Nature Switzerland, 2022.

17.Shaobo Lin, Xingyu Zeng, Rui Zhao.”A Unified Framework with Meta-dropout for Few-shot Learning.”arXivpreprint arXiv:2210.06409 (2022).

18.Shaobo Lin, Xingyu Zeng, Shilin Yan, Rui Zhao.”Three-stage training pipeline with patch random drop forfew-shot object detection.”Proceedings of the Asian Conference on Computer Vision. 2022.

19.Yingjie Cai, Buyu Li, Zeyu Jiao, Hongsheng Li, Xingyu Zeng, Xiaogang Wang.”Monocular 3d object detectionwith decoupled structured polygon estimation and height-guided depth estimation.”Proceedings of theAAAI Conference on Artificial Intelligence. Vol. 34. No. 07. 2020.

20.Xinzhu Ma, Shinan Liu, Zhiyi Xia, Hongwen Zhang, Xingyu Zeng, Wanli Ouyang.”Rethinking pseudo-lidarrepresentation.”Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28,2020, Proceedings, Part XIII 16. Springer International Publishing, 2020.

21.Peng Su, Kun Wang, Xingyu Zeng, Shixiang Tang, Dapeng Chen, Di Qiu, Xiaogang Wang.”Adapting objectdetectors with conditional domain normalization.”Computer Vision–ECCV 2020: 16th European Conference,Glasgow, UK, August 23–28, 2020, Proceedings, Part XI 16. Springer International Publishing, 2020.

22.Buyu Li, Wanli Ouyang, Lu Sheng, Xingyu Zeng, Xiaogang Wang.”Gs3d: An efficient 3d object detectionframework for autonomous driving.”Proceedings of the IEEE/CVF conference on computer vision and patternrecognition. 2019.

23.Xingyu Zeng, Wanli Ouyang, Junjie Yan, Hongsheng Li, Tong Xiao, Kun Wang, Yu Liu, Yucong Zhou, BinYang, Zhe Wang, Hui Zhou, Xiaogang Wang.”Crafting gbd-net for object detection.”IEEE transactions onpattern analysis and machine intelligence 40.9 (2017): 2109-2123.

24.Kai Kang, Hongsheng Li, Junjie Yan, Xingyu Zeng, Bin Yang, Tong Xiao, Cong Zhang, Zhe Wang, RuohuiWang, Xiaogang Wang, Wanli Ouyang.”T-cnn: Tubelets with convolutional neural networks for object detectionfrom videos.”IEEE Transactions on Circuits and Systems for Video Technology 28.10 (2017): 2896-2907.

25.Jingwei Guan, Shuai Yi, Xingyu Zeng, Wai-Kuen Cham, Xiaogang Wang.”Visual importance and distortionguided deep image quality assessment framework.”IEEE Transactions on Multimedia 19.11 (2017): 2505-2520.

26.Wanli Ouyang, Xingyu Zeng, Xiaogang Wang.”Learning mutual visibility relationship for pedestrian detectionwith a deep model.”International Journal of Computer Vision 120 (2016): 14-27.

27.Xingyu Zeng, Wanli Ouyang, Bin Yang, Junjie Yan, Xiaogang Wang.”Gated bi-directional cnn for objectdetection.”Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October11–14, 2016, Proceedings, Part VII 14. Springer International Publishing, 2016.

28.Xingyu Zeng, Wanli Ouyang, Xiaogang Wang.”Window-object relationship guided representation learningfor generic object detections.”arXiv preprint arXiv:1512.02736 (2015).

29.Wanli Ouyang, Xingyu Zeng, Xiaogang Wang.”Partial occlusion handling in pedestrian detection with a deepmodel.”IEEE Transactions on Circuits and Systems for Video Technology 26.11 (2015): 2123-2137.

30.Wanli Ouyang, Hongyang Li, Xingyu Zeng, Xiaogang Wang.”Learning deep representation with large-scaleattributes.”Proceedings of the IEEE International Conference on Computer Vision. 2015.

31.Wanli Ouyang, Xiaogang Wang, Xingyu Zeng, Shi Qiu, Ping Luo, Yonglong Tian, Hongsheng Li, Shuo Yang,Zhe Wang, Chen-Change Loy, Xiaoou Tang.”Deepid-net: Deformable deep convolutional neural networksfor object detection.”Proceedings of the IEEE conference on computer vision and pattern recognition. 2015.

32.Wanli Ouyang, Xingyu Zeng, Xiaogang Wang.”Single-pedestrian detection aided by two-pedestrian detection.”IEEE transactions on pattern analysis and machine intelligence 37.9 (2014): 1875-1889.

33.Wanli Ouyang, Ping Luo, Xingyu Zeng, Shi Qiu, Yonglong Tian, Hongsheng Li, Shuo Yang, Zhe Wang,Yuanjun Xiong, Chen Qian, Zhenyao Zhu, Ruohui Wang, Chen-Change Loy, Xiaogang Wang, Xiaoou Tang.”Deepid-net: multi-stage and deformable deep convolutional neural networks for object detection.”arXivpreprint arXiv:1409.3505 (2014).

34.Xingyu Zeng, Wanli Ouyang, Meng Wang, Xiaogang Wang.”Deep learning of scene-specific classifier forpedestrian detection.”Computer Vision–ECCV 2014: 13th European Conference, Zurich, Switzerland, September6-12, 2014, Proceedings, Part III 13. Springer International Publishing, 2014.

35.Xingyu Zeng, Wanli Ouyang, Xiaogang Wang.”Multi-stage contextual deep learning for pedestrian detection.”Proceedings of the IEEE International Conference on Computer Vision. 2013.

36.Wanli Ouyang, Xingyu Zeng, Xiaogang Wang.”Modeling mutual visibility relationship in pedestrian detection.”Proceedings of the IEEE conference on computer vision and pattern recognition. 2013.