Li

WenjieLi's activity

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

authored 2 papers 11 months ago

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

Paper • 2502.13946 • Published Feb 19, 2025 • 10

Sigma: Differential Rescaling of Query, Key and Value for Efficient Language Models

Paper • 2501.13629 • Published Jan 23, 2025 • 48

authored a paper about 1 year ago

Direct Preference Optimization Using Sparse Feature-Level Constraints

Paper • 2411.07618 • Published Nov 12, 2024 • 17

authored a paper over 1 year ago

OpenResearcher: Unleashing AI for Accelerated Scientific Research

Paper • 2408.06941 • Published Aug 13, 2024 • 32