Latent Adversarial Regularization for Offline Preference Optimization
Paper
•
2601.22083
•
Published
•
13
Enyi (Olivia) Jiang
EnyiJiang
·
AI & ML interests
AI Safety & Alignment
Recent Activity
updated
a collection
1 day ago
AI Safety and Alignment
updated
a collection
1 day ago
AI Safety and Alignment
updated
a collection
1 day ago
AI Safety and Alignment
Organizations
authored
4
papers
1 day ago
RAMP: Boosting Adversarial Robustness Against Multiple $l_p$ Perturbations for Universal Robustness
Paper
•
2402.06827
•
Published
Towards Universal Certified Robustness with Multi-Norm Training
Paper
•
2410.03000
•
Published
Misaligning Reasoning with Answers -- A Framework for Assessing LLM CoT Robustness
Paper
•
2505.17406
•
Published
submitted
a
paper
to Daily Papers
4 days ago