邬渊

职称:助理教授,博士生导师

毕业院校:加拿大卡尔顿大学

email:yuanwu@jlu.edu.cn

个人主页:

研究方向:迁移学习,机器学习泛化理论,大语言模型

个人简介

邬渊,78m威久国际v9捕鱼官网助理教授,博士生导师。研究方向为迁移学习,机器学习泛化理论。所涉及的应用有图像分类,图像语义分割,文本分类等。在AAAI,ECCV,ICASSP,AISTATS,TIST等国际会议\期刊发表文章7篇。


目前在探索大语言模型large language model (llm)。 本组与微软亚洲研究院,中科院自动化所,香港科技大学等单位合作发表首篇大语言模型评测综述论文 A Survey on Evaluation of Large Language Models. 


近几年计划的研究方向:(1) 大语言模型的评估 (The evaluation on large language models);(2) 可信大语言模型(Trustworthy large language models);(3)心理学与大语言模型的交叉研究(Applying psychology to improve large language models)。


欢迎对以上方向感兴趣的本科生、硕士生、博士生咨询!

(本组2024级博士名额已满)

工作经历

2022.11-至今 78m威久国际v9捕鱼官网 助理教授

教育经历

2018.09-2022.06   加拿大卡尔顿大学 计算机科学 博士 (导师:Dr. Ahemd El-Roby, Dr. Diana Inkpen.)

2015.09-2018.07   兰州大学 软件工程 硕士 (导师:李廉)

2008.09-2012.06   北京化工大学 计算机科学与技术 学士

论文选

详见个人Google scholar:https://scholar.google.com/citations?user=KVeRu2QAAAAJ&hl=zh-CN

部分论文信息如下:

[1] Wu, Y., & Guo, Y. (2020, April). Dual adversarial co-learning for multi-domain text classification. In Proceedings of the AAAI conference on artificial intelligence (Vol. 34, No. 04, pp. 6438-6445). (AAAI, CCF-A, 清华A类)

[2] Wu, Y., Inkpen, D., & El-Roby, A. (2020). Dual mixup regularized learning for adversarial domain adaptation. In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XXIX 16 (pp. 540-555). Springer International Publishing.(ECCV, CCF-B, 清华A类)

[3] Wu, Y., Inkpen, D., & El-Roby, A. (2021, June). Mixup regularized adversarial networks for multi-domain text classification. In ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 7733-7737). IEEE. (ICASSP, CCF-B, 清华B类)

[4] Wu, Y., Inkpen, D., & El-Roby, A. (2021). Towards category and domain alignment: Category-invariant feature enhancement for adversarial domain adaptation. In Proceedings of the IEEE/CVF International Conference on Computer Vision workshops (pp. 132-141). (ICCV workshop)

[5] Wu, Y., Inkpen, D., & El-Roby, A. (2021, April). Conditional Adversarial Networks for Multi-Domain Text Classification. In Proceedings of the Second Workshop on Domain Adaptation for NLP (pp. 16-27). (EACL workshop)

[6] Wu, Y., Inkpen, D., & El-Roby, A. (2022, May). Co-regularized adversarial learning for multi-domain text classification. In International Conference on Artificial Intelligence and Statistics (pp. 6690-6701). PMLR. (AISTATS, CCF-C, 清华B类)

[7] Wu, Y., Inkpen, D., & El-Roby, A. (2022, May). Maximum Batch Frobenius Norm for Multi-Domain Text Classification. In ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 3763-3767). IEEE. (ICASSP, CCF-B, 清华B类)

[8] Chang, Y., Wang, X., Wang, J., Wu, Y., Zhu, K., Chen, H., ...& Xie, X. (2023). A survey on evaluation of large language models. This paper will appear at ACM Transactions on Intelligent Systems and Technology.

[9] Hu, J., & Wu, Y. (2024, April). Regularized Conditional Alignment for Multi-Domain Text Classification. This paper will appear at ICASSP 2024.


社会兼职

会议审稿人: AAAI, EMNLP, AISTATS

期刊审稿人: Information Science, IEEE Transactions on Cybernetics, npj Digital Medicine, Financial Innovation.

获奖情况

EACL 2021, the Second Workshop on Domain Adaptation for NLP, Best paper award.

AISTATS 2022, Outstanding reviewer award.

返回上一层