liangliang's picture

1 2 1

liangliang

Fi-Liang

·

AI & ML interests

None yet

Recent Activity

commented on a paper 1 day ago

Are LLMs Vulnerable to Preference-Undermining Attacks (PUA)? A Factorial Analysis Methodology for Diagnosing the Trade-off between Preference Alignment and Real-World Validity

upvoted a paper 1 day ago

Are LLMs Vulnerable to Preference-Undermining Attacks (PUA)? A Factorial Analysis Methodology for Diagnosing the Trade-off between Preference Alignment and Real-World Validity

liked a model 7 months ago

TeleAI-AI-Flow/AI-Flow-Ruyi-7B-Preview0704

View all activity

Organizations

None yet

upvoted a paper 1 day ago

Are LLMs Vulnerable to Preference-Undermining Attacks (PUA)? A Factorial Analysis Methodology for Diagnosing the Trade-off between Preference Alignment and Real-World Validity

Paper • 2601.06596 • Published 6 days ago • 11

upvoted a paper about 1 year ago

Physics in Next-token Prediction

Paper • 2411.00660 • Published Nov 1, 2024 • 14