陈薇，中国科学院计算技术研究所研究员、博士生导师，现任智能算法安全全国重点实验室副主任，曾任微软亚洲研究院计算学习理论组负责人。长期从事机器学习基本理论与方法方向的研究，担任中科院战略性先导科技专项项目负责人，在深度学习机理、分布式优化、安全可信应用等方面取得科研成果，在本领域国际重要学术会议与期刊发表学术论文70余篇（如ICML、NeurIPS、ICLR等），入选2021年度福布斯中国科技女性榜、2023年度麻省理工科技评论智能计算创新人物、2024年度中国科学院大学小米青年学者。担任本领域主要学术会议ICML、NeurIPS、AAAI的程序委员会高级领域主席、领域主席等。

2022年2月 — 今：中国科学院计算技术研究所，研究员

2011年7月 — 2022年2月： 微软亚洲研究院，Associate Researcher，Researcher，Lead Researcher，Principal Research Manager 

2006年9月 — 2011年7月：中国科学院数学与系统科学研究院，博士

2002年9月 — 2006年7月：山东大学，数学与系统科学学院，学士

学术专著：

• 刘铁岩，陈薇，王太峰，高飞，《分布式机器学习：算法、理论与实践》，机械工业出版社，北京，2018(ISBN 978-7-111-60918-6)

期刊/会议文章：

[1] Wenjie Zhou, Bohan Wang, Wei Chen, Xueqi Cheng, BSFA: Leveraging the Subspace Dichotomy to Accelerate Neural Network Training. 2025 Conference on Empirical Methods in Natural Language Processing. (EMNLP), 2025.

[2] Junjie Nan, Jianing Li, Wei Chen, Mingkun Zhang, Xueqi Cheng, NAPPure: Adaversarial Purification for Robust Image Classification under Non-Additive Perturbations. IEEE/CVF International Conference on Computer Vision (ICCV), 2025.

[3] Yuchen Wen, Keping Bi, Wei Chen, Jiafeng Guo, Xueqi Cheng, Evaluating Implicit Bias in Large Language Models by Attacking From a Psychometric Perspective. Findings of the Association for Computational Linguistics (ACL), 2025. (Project Webpage)

[4] Mingkun Zhang, Keping Bi, Wei Chen, Jiafeng Guo, Xueqi Cheng, CLIPure: Purification in Latent Space via CLIP for Adversarially Robust Zero-Shot Classification.The 13rd International Conference on Learning Representations(ICLR), 2025.

[5] Mingkun Zhang, Keping Bi, Wei Chen, Quanrun Chen, Jiafeng Guo, Xueqi Cheng, CausalDiff: Causality-Inspired Disentanglement via Difussion Model for Adversarial Defense. The 38th Annual Conference on Neural Information Processing systems(NeurIPS), 2024.

[6] Mingkun Zhang, Jianing Li, Wei Chen, Jiafeng Guo, Xueqi Cheng, Classifier Guidance Enhances Diffusion-based Purification by Preserviong Predictive Information. The 27th European Conference on Artifitial Intelligence(ECAI), 2024.

[7] Bohan Wang, Huishuai Zhang, Qi Meng, Ruoyu Sun, Zhi-Ming Ma, Wei Chen, Randomly-reshuffled Adam can provably converge under non-uniform smoothness. The 30th SIGKDD Conference on Knowledge Discovery and Data Mining (SIGKDD), 2024.

[8] Wenjie Zhou, Bohan Wang, Wei Chen, Zhi-Ming Ma, Xueqi Cheng, Momentum Gradient Descent over single-neuron linear network: rich behaviors of limiting Sharpness. Bridging the Gap Between Practice and Theory in Deep Learning (BGPT) ICLR workshop, 2024.

[9] Yu-An Liu, Ruqing Zhang, Mingkun Zhang, Jiafeng Guo, Maarten de Rijke, Wei Chen, Xueqi Cheng, Perturbation-Invariant Adversarial Training for Neural Ranking Models: Improving the Effectiveness-Robustness Trade-Off. The 38th International Association for the Advancement of Artificial Intelligence Conference (AAAI), 2024.

[10] Bohan Wang, Jingwen Fu, Huishuai Zhang, Nanning Zheng, Wei Chen. Closing the Gap between the Upper Bound and Lower Bound of Adam’s Iteration Complexity. Advances in Neural Information Processing Systems 37 (NeurIPS), 2023

[11] Lu Chen, Ruqing Zhang, Wei Huang, Wei Chen, Jiafeng Guo, Xueqi Cheng, Inducing Causal Structure for Abstractive Text Summarization. The 32nd ACM International Conference on Information and Knowledge Management (CIKM), 2023.