电话：
邮箱： dengwj16@sz.tsinghua.edu.cn
地址：
2019年7月-2023年10月，澳大利亚国立大学，计算机科学专业，博士
2016年9月-2019年6月，中国科学院大学，计算机应用专业，硕士
2012年9月-2016年6月，北京交通大学，电子科学与技术专业，学士
2026年6月-至今，清华大学深圳国际研究生院，助理教授/特别研究员
2025年2月-2026 年 5 月，澳大利亚国立大学，博后研究员
2023年1月-2025年1月，澳大利亚国立大学，博士后
Transactions on Machine Learning Research 副主编
自主评估、自主探索与自主提升的智能体
致力于构建能够自主评估能力边界、自主探索未知环境并持续自我提升的智能体。研究聚焦无监督泛化评估、模型可靠性分析、基础模型与三维智能，推动人工智能从依赖人工标注与反馈向自主学习、自主进化范式发展。
1. Weijian Deng, Dylan Campbell, Chunyi Sun, Shubham Kanitkar, Matthew E. Shaffer, and Stephen Gould. Differentiable neural surface refinement for modeling transparent objects[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2024: 20268–20277.
2. Weijian Deng*, Yumin Suh, Stephen Gould, and Liang Zheng. Confidence and dispersity speak: Confidence and dispersity speak: Characterizing prediction matrix for unsupervised accuracy estimation[C]//Proceedings of the International Conference on Machine Learning (ICML). PMLR, 2023: 7658–7674.
3. WeijianDeng, Stephen Gould, and Liang Zheng.On the strong correlation between model invariance and generalization[C]//Advances in Neural Information Processing Systems (NeurIPS). 2022: 28052–28067.
4. WeijianDeng, and Liang Zheng*. AutoEval: Are Labels Always Necessary for Classifier Accuracy Evaluation?[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, Dec. 2021, 46(3): 1868–1880.
5. Weijian Deng, Liang Zheng, Qixiang Ye, Guoliang Kang, Yi Yang, Jianbin Jiao*. Image-image domain adaptation with preserved self-similarity and domain-dissimilarity for person re-identification[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018: 994–1003.
6. Weijian Deng, Stephen Gould, Liang Zheng*. What does rotation prediction tell us about classifier accuracy under varying testing environments? [C]//Proceedings of the International Conference on Machine Learning (ICML), 2021: 2579–2589.
7. Weijian Deng, Dylan Campbell, Chunyi Sun, Jiahao Zhang, Shubham Kanitkar, Matthew E. Shaffer, Stephen Gould. Pos3r: 6D pose estimation for unseen objects made easy[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025: 16818–16828.
8. Yuli Zou#*, Weijian Deng#, Liang Zheng. Adaptive Calibrator Ensemble: Navigating Test Set Difficulty in Out-of-Distribution Scenarios[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2023: 19333–19342.
9. Weijian Deng, Joshua Marsh, Stephen Gould, Liang Zheng*. Fine-grained classification via categorical memory networks[J]. IEEE Transactions on Image Processing, 2022, 31: 4186–4196.
10. WeijieTu, Weijian Deng*, and Tom Gedeon. Toward a Holistic Evaluation of Robustness in CLIP Models[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, Jun. 2025, 47(9): 8280–8296.
1. Weijian Deng, Dylan Campbell, Chunyi Sun, Shubham Kanitkar, Matthew E. Shaffer, and Stephen Gould. Differentiable neural surface refinement for modeling transparent objects[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2024: 20268–20277.
2. Weijian Deng*, Yumin Suh, Stephen Gould, and Liang Zheng. Confidence and dispersity speak: Confidence and dispersity speak: Characterizing prediction matrix for unsupervised accuracy estimation[C]//Proceedings of the International Conference on Machine Learning (ICML). PMLR, 2023: 7658–7674.
3. WeijianDeng, Stephen Gould, and Liang Zheng.On the strong correlation between model invariance and generalization[C]//Advances in Neural Information Processing Systems (NeurIPS). 2022: 28052–28067.
4. WeijianDeng, and Liang Zheng*. AutoEval: Are Labels Always Necessary for Classifier Accuracy Evaluation?[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, Dec. 2021, 46(3): 1868–1880.
5. Weijian Deng, Liang Zheng, Qixiang Ye, Guoliang Kang, Yi Yang, Jianbin Jiao*. Image-image domain adaptation with preserved self-similarity and domain-dissimilarity for person re-identification[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018: 994–1003.
6. Weijian Deng, Stephen Gould, Liang Zheng*. What does rotation prediction tell us about classifier accuracy under varying testing environments? [C]//Proceedings of the International Conference on Machine Learning (ICML), 2021: 2579–2589.
7. Weijian Deng, Dylan Campbell, Chunyi Sun, Jiahao Zhang, Shubham Kanitkar, Matthew E. Shaffer, Stephen Gould. Pos3r: 6D pose estimation for unseen objects made easy[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025: 16818–16828.
8. Yuli Zou#*, Weijian Deng#, Liang Zheng. Adaptive Calibrator Ensemble: Navigating Test Set Difficulty in Out-of-Distribution Scenarios[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2023: 19333–19342.
9. Weijian Deng, Joshua Marsh, Stephen Gould, Liang Zheng*. Fine-grained classification via categorical memory networks[J]. IEEE Transactions on Image Processing, 2022, 31: 4186–4196.
10. WeijieTu, Weijian Deng*, and Tom Gedeon. Toward a Holistic Evaluation of Robustness in CLIP Models[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, Jun. 2025, 47(9): 8280–8296.
国家青年人才项目，2025
DAAD AINeT Fellow in Explainable AI, 2025
CVPR 2025 Outstanding Reviewer, 2025
NeurIPS 2024 Top Reviewer, 2024
ACM MM 2024 Outstanding Area Chair, 2024
NeurIPS 2023 Top Reviewer, 2023
ICML 2022 Top 10% Reviewer, 2022
ECCV 2020 Outstanding Reviewer, 2022
Australian Government Research Training Program (AGRTP) Scholarship, 2019-2023
国家青年人才项目，2025
DAAD AINeT Fellow in Explainable AI, 2025
CVPR 2025 Outstanding Reviewer, 2025
NeurIPS 2024 Top Reviewer, 2024
ACM MM 2024 Outstanding Area Chair, 2024
NeurIPS 2023 Top Reviewer, 2023
ICML 2022 Top 10% Reviewer, 2022
ECCV 2020 Outstanding Reviewer, 2022
Australian Government Research Training Program (AGRTP) Scholarship, 2019-2023
