Elias Abad Rocamora (2026)

Research Interests:

Adversarial Training
Robustness Verification
Optimization

Biography

I received my BSc in Data Science and Engineering from Universitat Politècnica de Catalunya (UPC) in Barcelona, Spain in 2022. I then moved to Madrid to obtain my MSc in Applied Mathematics from Universidad Carlos III de Madrid (UC3M) in 2023. I conducted both my BSc and MSc thesis at LIONS. Subsequently, in September 2023 I started my PhD, also at LIONS, which I finished in February 2026. My hobbies are running, cycling, climbing and any mountain-related activity.

Robustness in Both Domains: CLIP Needs a Robust Text Encoder

E. Abad Rocamora; C. Schlarmann; N. Singh; Y. Wu; M. Hein et al.

2025. 39th Conference on Neural Information Processing Systems (NeurIPS 2025), San Diego, USA, 2025-12-02 – 2025-12-07.

Detailed record

Linear Attention for Efficient Bidirectional Sequence Modeling

A. Afzal; E. Abad Rocamora; L. Candogan; P. Puigdemont; F. Tonin et al.

2025. 39th Conference on Neural Information Processing Systems (NeurIPS 2025), San Diego, USA, 2025-12-02 – 2025-12-07.

Detailed record

Certified Robustness Under Bounded Levenshtein Distance

E. Abad Rocamora; G. Chrysos; V. Cevher

2025. The Thirteenth International Conference on Learning Representations, Singapore, 2025-04-24-2025-04-28.

Detailed record

Single-pass Detection of Jailbreaking Input in Large Language Models

L. Candogan; Y. Wu; E. Abad Rocamora; G. Chrysos; V. Cevher

Transactions on Machine Learning Research. 2025. Vol. 02/2025.

Detailed record

Membership Inference Attacks against Large Vision-Language Models

Zhan Li; Y. Wu; Y. Chen; F. Tonin; E. Abad Rocamora et al.

2024. 38th Annual Conference on Neural Information Processing Systems, Vancouver Convention Center, 2024-12-10 – 2024-12-15.

Detailed record

Revisiting Character-level Adversarial Attacks for Language Models

E. Abad Rocamora; Y. Wu; F. Liu; G. Chrysos; V. Cevher

2024. 41st International Conference on Machine Learning (ICML 2024), Vienna, Austria, July 21-27, 2024.

Detailed record

Efficient local linearity regularization to overcome catastrophic overfitting

E. Abad Rocamora; F. Liu; G. Chrysos; P. M. Olmos; V. Cevher

2024. 12th International Conference on Learning Representations (ICLR 2024), Vienna, Austria, May 7-11, 2024.

Detailed record

Sound and Complete Verification of Polynomial Networks

E. Abad Rocamora; M. F. Sahin; F. Liu; G. Chrysos; V. Cevher

2022. 36th Conference on Neural Information Processing Systems (NeurIPS), New Orleans, USA, November 28 – December 3, 2022.

Detailed record

Contact

e-mail address: Elias Abad Rocamora

EPFL people page