Hugging Face's logo
Taiwei Shi's picture
16 26 4

Taiwei Shi

MaksimSTW
21world's profile picture Sarverott's profile picture MichaelR207's profile picture
·
https://taiweis.com

AI & ML interests

reinforcement learning, alignment, human-AI collaboration, and computational social science

Recent Activity

authored a paper 1 day ago
The Blind Spot of Agent Safety: How Benign User Instructions Expose Critical Vulnerabilities in Computer-Use Agents
liked a dataset 1 day ago
lime-nlp/OS-Blind
upvoted a paper 1 day ago
The Blind Spot of Agent Safety: How Benign User Instructions Expose Critical Vulnerabilities in Computer-Use Agents
View all activity

Organizations

Social And Language Technology Lab's profile picture Taiwei's Team's profile picture Language, Intelligence, and Model Evaluation Lab's profile picture