师资队伍

吴泳涛

您当前所在的位置： 首页> 师资队伍> 专任教师> 吴泳涛

吴泳涛讲师

返回列表

邮箱：yongtaowu@ruc.edu.cn

中国人民大学高瓴人工智能学院讲师。2026年获瑞士洛桑联邦理工学院（EPFL）博士学位，曾任加州大学洛杉矶分校（UCLA）访问学者。主要研究方向为机器学习理论与优化，重点从优化理论视角研究神经网络的训练动力学；同时也将优化方法应用于可信大模型研究。在 NeurIPS、ICML、ICLR、IEEE TPAMI 等人工智能领域重要会议和期刊发表论文10余篇。曾组织瑞士洛桑联邦理工学院数字信任中心大模型微调陷阱研讨会，并协助组织 NeurIPS 2024 FITML 研讨会。曾获瑞典皇家理工学院年度奖学金。长期担任 NeurIPS、ICLR、ICML、AISTATS、IJCV、TMLR 等国际会议和期刊审稿人。

教育经历

2022-2026年瑞士洛桑联邦理工学院博士

2020-2022年瑞典皇家理工学院硕士

2016-2020年中山大学本科

教授课程

研究方向

机器学习理论（泛化理论与学习理论）

神经网络优化与训练动力学

可信机器学习（鲁棒性、安全性与隐私）

学术论文

2026

DiffCAP: Diffusion-based Cumulative Adversarial Purification for Vision Language Models

Jia Fu, Yongtao Wu, Yihang Chen, Kunyu Peng, Xiao Zhang, Volkan Cevher, Sepideh Pashami, Anders Holst

Transactions on Machine Learning Research

2025

Hadamard Product in Deep Learning: Introduction, Advances and Challenges

Grigorios Chrysos, Yongtao Wu, Razvan Pascanu, Philip Torr, Volkan Cevher

Transactions on Pattern Analysis and Machine Intelligence

Multi-Step Alignment as Markov Games: An Optimistic Online Gradient Descent Approach with Convergence Guarantees

Yongtao Wu (共同一作), Luca Viano，Yihang Chen, Zhenyu Zhu, Kimon Antonakopoulos, Quanquan Gu, Volkan Cevher

Transactions on Machine Learning Research

Quantum-PEFT: Ultra Parameter-efficient Fine-tuning

Toshiaki Koike-Akino, Francesco Tonin, Yongtao Wu, Zhenqing Wu, Leyla Naz Candogan, Volkan Cevher

International Conference on Learning Representations

Robustness in Both Domains: CLIP Needs a Robust Text Encoder

Elias Abad Rocamora, Christian Schlarmann, Naman Deep Singh, Yongtao Wu, Matthias Hein, Volkan Cevher

Conference on Neural Information Processing Systems

Linear Attention for Efficient Bidirectional Sequence Modeling

Arshia Afzal, Elias Abad Rocamora, Leyla Naz Candogan, Pol Puigdemont, Francesco Tonin, Yongtao Wu, Mahsa Shoaran, Volkan Cevher

Conference on Neural Information Processing Systems

2024

Robust NAS under Adversarial Training: Benchmark, Theory, and Beyond

Yongtao Wu, Fanghui Liu, Carl-Johann Simon-Gabriel, Grigorios Chrysos, Volkan Cevher

International Conference on Learning Representations

Revisiting Character-level Adversarial Attacks for Language Models

Elias Abad Rocamora, Yongtao Wu (通讯作者), Fanghui Liu, Grigorios G. Chrysos, Volkan Cevher

International Conference on Machine Learning

Membership Inference Attacks against Large Vision-Language Models

Zhan Li, Yongtao Wu (共同一作), Yihang Chen, Francesco Tonin, Elias Abad Rocamora, Volkan Cevher

Conference on Neural Information Processing Systems

Universal Gradient Methods for Stochastic Convex Optimization

Anton Rodomanov, Ali Kavis, Yongtao Wu, Kimon Antonakopoulos, Volkan Cevher

International Conference on Machine Learning

Single-pass Detection of Jailbreaking Input in Large Language Models

Leyla Naz Candogan, Yongtao Wu, Elias Abad Rocamora, Grigorios G. Chrysos, Volkan Cevher

Transactions on Machine Learning Research

2023

On the Convergence of Encoder-only Shallow Transformers

Yongtao Wu, Fanghui Liu, Grigorios G Chrysos, Volkan Cevher

Conference on Neural Information Processing Systems

2022

Extrapolation and Spectral Bias of Neural Nets with Hadamard Product: a Polynomial Net Study

Yongtao Wu, Zhenyu Zhu, Fanghui Liu, Grigorios G Chrysos, Volkan Cevher

Conference on Neural Information Processing Systems

师资队伍

吴泳涛

吴泳涛 讲师

教育经历

教授课程

研究方向

学术论文

2026

DiffCAP: Diffusion-based Cumulative Adversarial Purification for Vision Language Models

Jia Fu, Yongtao Wu, Yihang Chen, Kunyu Peng, Xiao Zhang, Volkan Cevher, Sepideh Pashami, Anders Holst

Transactions on Machine Learning Research

2025

Hadamard Product in Deep Learning: Introduction, Advances and Challenges

Grigorios Chrysos, Yongtao Wu, Razvan Pascanu, Philip Torr, Volkan Cevher

Transactions on Pattern Analysis and Machine Intelligence

Multi-Step Alignment as Markov Games: An Optimistic Online Gradient Descent Approach with Convergence Guarantees

Yongtao Wu (共同一作), Luca Viano，Yihang Chen, Zhenyu Zhu, Kimon Antonakopoulos, Quanquan Gu, Volkan Cevher

Transactions on Machine Learning Research

Quantum-PEFT: Ultra Parameter-efficient Fine-tuning

Toshiaki Koike-Akino, Francesco Tonin, Yongtao Wu, Zhenqing Wu, Leyla Naz Candogan, Volkan Cevher

International Conference on Learning Representations

Robustness in Both Domains: CLIP Needs a Robust Text Encoder

Elias Abad Rocamora, Christian Schlarmann, Naman Deep Singh, Yongtao Wu, Matthias Hein, Volkan Cevher

Conference on Neural Information Processing Systems

Linear Attention for Efficient Bidirectional Sequence Modeling

Arshia Afzal, Elias Abad Rocamora, Leyla Naz Candogan, Pol Puigdemont, Francesco Tonin, Yongtao Wu, Mahsa Shoaran, Volkan Cevher

Conference on Neural Information Processing Systems

2024

Robust NAS under Adversarial Training: Benchmark, Theory, and Beyond

Yongtao Wu, Fanghui Liu, Carl-Johann Simon-Gabriel, Grigorios Chrysos, Volkan Cevher

International Conference on Learning Representations

Revisiting Character-level Adversarial Attacks for Language Models

Elias Abad Rocamora, Yongtao Wu (通讯作者), Fanghui Liu, Grigorios G. Chrysos, Volkan Cevher

International Conference on Machine Learning

Membership Inference Attacks against Large Vision-Language Models

Zhan Li, Yongtao Wu (共同一作), Yihang Chen, Francesco Tonin, Elias Abad Rocamora, Volkan Cevher

Conference on Neural Information Processing Systems

Universal Gradient Methods for Stochastic Convex Optimization

Anton Rodomanov, Ali Kavis, Yongtao Wu, Kimon Antonakopoulos, Volkan Cevher

International Conference on Machine Learning

Single-pass Detection of Jailbreaking Input in Large Language Models

Leyla Naz Candogan, Yongtao Wu, Elias Abad Rocamora, Grigorios G. Chrysos, Volkan Cevher

Transactions on Machine Learning Research

2023

On the Convergence of Encoder-only Shallow Transformers

Yongtao Wu, Fanghui Liu, Grigorios G Chrysos, Volkan Cevher

Conference on Neural Information Processing Systems

2022

Extrapolation and Spectral Bias of Neural Nets with Hadamard Product: a Polynomial Net Study

Yongtao Wu, Zhenyu Zhu, Fanghui Liu, Grigorios G Chrysos, Volkan Cevher

Conference on Neural Information Processing Systems

吴泳涛讲师