Yuming Yang

Umean's activity

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

upvoted a paper 4 months ago

Analyzing the Effects of Supervised Fine-Tuning on Model Knowledge from Token and Parameter Levels

Paper • 2509.16596 • Published Sep 20, 2025 • 14

upvoted 2 papers 6 months ago

Reasoning or Memorization? Unreliable Results of Reinforcement Learning Due to Data Contamination

Paper • 2507.10532 • Published Jul 14, 2025 • 89

Pre-Trained Policy Discriminators are General Reward Models

Paper • 2507.05197 • Published Jul 7, 2025 • 39

upvoted a collection 6 months ago

POLAR

Collection

5 items • Updated 9 days ago • 13

upvoted a paper 7 months ago

Measuring Data Diversity for Instruction Tuning: A Systematic Analysis and A Reliable Metric

Paper • 2502.17184 • Published Feb 24, 2025 • 1