Yongtao Wu

PhD student, Swiss Federal Institute of Technology Lausanne

Joined

May 2022

Names

Yongtao Wu (Preferred)

Emails

****@epfl.ch (Confirmed)

****@kth.se (Confirmed)

Personal Links

Homepage

Google Scholar

DBLP

Career & Education History

PhD student

Swiss Federal Institute of Technology Lausanne (epfl.ch)

2022 – Present

Advisors, Relations & Conflicts

PhD Advisor

Volkan Cevher

2022 – Present

Expertise

trustworthy machine learning

2023 – Present

machine learning

2022 – Present

Publications

Multi-Step Alignment as Markov Games: An Optimistic Online Mirror Descent Approach with Convergence Guarantees
Yongtao Wu, Luca Viano, Kimon Antonakopoulos, Yihang Chen, Zhenyu Zhu, Quanquan Gu, Volkan Cevher
- Accepted by TMLR
- Readers: Everyone
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
- Submitted to ICLR 2026
- Readers: Everyone
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
- NeurIPS 2025 poster
- Readers: Everyone
Robustness in Both Domains: CLIP Needs a Robust Text Encoder
Elias Abad Rocamora, Christian Schlarmann, Naman Deep Singh, Yongtao Wu, Matthias Hein, Volkan Cevher
- NeurIPS 2025 poster
- Readers: Everyone
Single-pass Detection of Jailbreaking Input in Large Language Models
Leyla Naz Candogan, Yongtao Wu, Elias Abad Rocamora, Grigorios Chrysos, Volkan Cevher
- Accepted by TMLR
- Readers: Everyone
Imbalance-Regularized LoRA: A Plug-and-Play Method for Improving Fine-Tuning of Foundation Models
Zhenyu Zhu, Yongtao Wu, Quanquan Gu, Volkan Cevher
- AFM 2024 Poster
- Readers: Everyone
Multi-Step Preference Optimization via Two-Player Markov Games
Yongtao Wu, Luca Viano, Yihang Chen, Zhenyu Zhu, Quanquan Gu, Volkan Cevher
- LanGame Poster
- Readers: Everyone
Quantum-PEFT: Ultra parameter-efficient fine-tuning
Toshiaki Koike-Akino, Francesco Tonin, Yongtao Wu, Frank Zhengqing Wu, Leyla Naz Candogan, Volkan Cevher
- ICLR 2025 Poster
- Readers: Everyone
LION: A bidirectional framework that trains like a Transformer and infers like an RNN
Arshia Afzal, Elias Abad Rocamora, Leyla Naz Candogan, Pol Puigdemont, Francesco Tonin, Yongtao Wu, Mahsa Shoaran, Volkan Cevher
- Submitted to ICLR 2025
- Readers: Everyone
Imbalance-Regularized LoRA: A Plug-and-Play Method for Improving Fine-Tuning of Foundation Models
Zhenyu Zhu, Yongtao Wu, Quanquan Gu, Volkan Cevher
- Submitted to ICLR 2025
- Readers: Everyone

View all 20 publications

Co-Authors

View all 28 co-authors