Zeming Wei

ZemingWei's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored a paper 4 months ago

False Sense of Security: Why Probing-based Malicious Input Detection Fails to Generalize

Paper • 2509.03888 • Published Sep 4 • 3

authored a paper over 1 year ago

Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Paper • 2310.06387 • Published Oct 10, 2023