Tony He

ttttonyhe

·

https://lipeng.ac

AI & ML interests

Trustworthy Machine Learning

Recent Activity

updated a model about 1 month ago

ttttonyhe/Qwen3-4B-Instruct-RETA

upvoted a paper about 1 month ago

Defending against Adaptive Prompt Injection Attacks via Reasoning-enabled Task Alignment

updated a collection about 1 month ago

Prompt Injection

View all activity

Organizations

Collections 17

View 17 collections

Papers 6

arxiv:2606.15441

arxiv:2601.01887

arxiv:2510.12117

arxiv:2505.20139

models 6

ttttonyhe/Qwen3-4B-Instruct-RETA

Text Generation • 4B • Updated about 1 month ago • 161

ttttonyhe/Qwen3-4B-Instruct-MetaSecAlign

Text Generation • 4B • Updated Jul 31 • 155

ttttonyhe/locket-deepseek-math-7b-mmlu

Text Generation • Updated Jun 14 • 32

ttttonyhe/locket-deepseek-math-7b-sql

Text Generation • Updated Jun 14 • 24

ttttonyhe/locket-deepseek-math-7b-samsum

Text Generation • Updated Jun 14 • 26

ttttonyhe/locket-deepseek-math-7b-math

Text Generation • Updated Jun 14 • 30

datasets 1

ttttonyhe/locket-data

Updated Jun 19 • 102