X-Teaming: Multi-Turn Jailbreaks and Defenses with Adaptive Multi-Agents
Paper
•
2504.13203
•
Published
•
35
•
2
Salman Rahman PRO
salmannyu
AI & ML interests
Natural Language Processing, Deep Learning, Scalable Oversight, and Language Model Evaluation
Recent Activity
upvoted
a
paper
24 days ago
WebOperator: Action-Aware Tree Search for Autonomous Agents in Web Environment
upvoted
a
paper
about 1 month ago
On the Interplay of Pre-Training, Mid-Training, and RL on Reasoning Language Models
upvoted
a
paper
about 1 month ago
SPARK: Stepwise Process-Aware Rewards for Reference-Free Reinforcement Learning
Organizations
