PsychoXiong's picture

2

PsychoXiong

PsychoO

AI & ML interests

None yet

Recent Activity

upvoted a paper 3 days ago

TROJail: Trajectory-Level Optimization for Multi-Turn Large Language Model Jailbreaks with Process Rewards

upvoted a paper 7 months ago

Quantile Advantage Estimation for Entropy-Safe Reasoning

View all activity

Organizations

None yet

upvoted a paper 3 days ago

TROJail: Trajectory-Level Optimization for Multi-Turn Large Language Model Jailbreaks with Process Rewards

Paper • 2512.07761 • Published 12 days ago • 1

upvoted a paper 7 months ago

Quantile Advantage Estimation for Entropy-Safe Reasoning

Paper • 2509.22611 • Published Sep 26, 2025 • 120