Li Pengyi

LiPengyi29's activity

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

upvoted a paper about 2 months ago

MaxInfo: A Training-Free Key-Frame Selection Method Using Maximum Volume for Enhanced Video Understanding

Paper • 2502.03183 • Published Feb 5 • 3

upvoted a paper 2 months ago

I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders

Paper • 2503.18878 • Published Mar 24 • 118