Li

Li on Hugging Face Daily Papers: 4 papers, 2 in the top 3 of their day, 106 upvotes.

1. Why Safeguarded Ships Run Aground? Aligned Large Language Models' Safety Mechanisms Tend to Be Anchored in The Template Region 9 upvotes, #14 of 2025-02-20
2. Sigma: Differential Rescaling of Query, Key and Value for Efficient Language Models 40 upvotes, #3 of 2025-01-24
3. Direct Preference Optimization Using Sparse Feature-Level Constraints 15 upvotes, #3 of 2024-11-14
4. OpenResearcher: Unleashing AI for Accelerated Scientific Research 28 upvotes, #5 of 2024-08-14

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.