miaozq's picture

3 3 6

miaozq

miaozq

·

AI & ML interests

M.S. @ Shanghai AI Lab｜LLM Security Research

Recent Activity

upvoted a collection 3 days ago

upvoted a paper 9 days ago

Toward Efficient Agents: Memory, Tool learning, and Planning

new activity 24 days ago

miaozq/Visco-Attack:image paths in some 'json' files are wrong

View all activity

Organizations

None yet

upvoted a collection 3 days ago

AgentDoG

A Diagnostic Guardrail Framework for AI Agent Safety and Security • 11 items • Updated 2 days ago • 81

upvoted a paper 9 days ago

Toward Efficient Agents: Memory, Tool learning, and Planning

Paper • 2601.14192 • Published 10 days ago • 51

upvoted a paper 8 months ago

Sherlock: Self-Correcting Reasoning in Vision-Language Models

Paper • 2505.22651 • Published May 28, 2025 • 48