Ivan Evtimov

How Vulnerable Are AI Agents to Indirect Prompt Injections? Insights from a Large-Scale Public Competition

arXiv 2026

AgentDAM: Privacy Leakage Evaluation for Autonomous Web Agents

arXiv 2025

Safety Alignment of LMs via Non-cooperative Games

arXiv 2025

Seamless: Multilingual Expressive and Streaming Speech Translation

arXiv 2023

Code Llama: Open Foundation Models for Code

arXiv 2023

A Whac-A-Mole Dilemma: Shortcuts Come in Multiples Where Mitigating One Amplifies Others

CVPR 2023 1

Arman Zharmagambetov

Kamalika Chaudhuri

Artyom Kozhevnikov

Cristian Canton Ferrer

Ilia Kulikov

Aaron Grattafiori

Abinesh Ramakrishnan

Albert Gordo

Alex Mourachko

Alexandre Défossez