← Authors

Sophie Xhonneux

3 papers · 2024–2025 · 2 conferences · across top CS/AI conferences

Achievements

๐ŸŒ Conference Polyglot (2) ๐ŸŒ‰ Interdisciplinary Bridge ๐Ÿ Cross-Pollinator (15)

Conferences

NIPS (2) ICLR (1)

Top co-authors

Stephan Gรผnnemann (2) Gauthier Gidel (2) Leo Schwinn (2) Alessandro Sordoni (1) David Dobre (1) Rishabh Agarwal (1) Shengyi Huang (1) Michael Noukhovitch (1) Aaron Courville (1) Arian Hosseini (1)

Keywords

adversarial attack (2) model unlearning (1) adversarial training (1) safety alignment (1) model alignment (1) language model (1) jailbreak attack (1) embedding space (1) large language model (1)

Papers

Asynchronous RLHF: Faster and More Efficient Off-Policy RL for Language Models ICLR 2025
Efficient Adversarial Training in LLMs with Continuous Attacks NIPS 2024
Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Space NIPS 2024