Tao Liu

utaotao's activity

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

authored 3 papers 1 day ago

Timber: Training-free Instruct Model Refining with Base via Effective Rank

Paper • 2509.23595 • Published Sep 28, 2025 • 1

Revisiting Model Interpolation for Efficient Reasoning

Paper • 2510.10977 • Published Oct 13, 2025 • 9

ProFit: Leveraging High-Value Signals in SFT via Probability-Guided Token Selection

Paper • 2601.09195 • Published 7 days ago • 12