Cooper Leong's picture

Cooper Leong

cooperleong00

·

https://cooperleong00.github.io/

AI & ML interests

None yet

Recent Activity

authored a paper 17 days ago

Why Safeguarded Ships Run Aground? Aligned Large Language Models' Safety Mechanisms Tend to Be Anchored in The Template Region

authored a paper 17 days ago

Instruct Once, Chat Consistently in Multiple Rounds: An Efficient Tuning Framework for Dialogue

authored a paper 17 days ago

TokenSkip: Controllable Chain-of-Thought Compression in LLMs

View all activity

Organizations

None yet

Collections 1

Papers 7

arxiv:2502.13946

arxiv:2502.12067

arxiv:2411.07618

arxiv:2410.06638

models 3

cooperleong00/Qwen2.5-7B-Instruct-Jailbroken

Updated Dec 23, 2024 • 28 • 1

cooperleong00/Meta-Llama-3-8B-Instruct-Jailbroken

Updated Dec 23, 2024 • 252 • 3

cooperleong00/deberta-v3-large_toxicity-scorer

Text Classification • Updated Feb 29, 2024 • 599 • 4

datasets

None public yet