yuxiao yang

yuxiaoyang's activity

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

upvoted 2 papers 21 days ago

An RL View of OPD: Least Square Policy Distillation for Sample-Efficient LLM Reasoning

Paper • 2609.35505 • Published 23 days ago • 32

Rethinking Training-Inference Mismatch in LLM Reinforcement Learning: Where It Arises and How to Correct It

Paper • 2609.32444 • Published 25 days ago • 36

authored a paper about 1 month ago

When EOS Tokens Disagree: Understanding Length Inflation in On-Policy Distillation

Paper • 2609.20511 • Published Sep 17 • 143

commented a paper about 1 month ago

When EOS Tokens Disagree: Understanding Length Inflation in On-Policy Distillation

Paper • 2609.20511 • Published Sep 17 • 143 •

5

upvoted a paper about 1 month ago

When EOS Tokens Disagree: Understanding Length Inflation in On-Policy Distillation

Paper • 2609.20511 • Published Sep 17 • 143

published a dataset about 2 months ago

yuxiaoyang/OPD-Rethink-Eval-Results

Updated Sep 5 • 4

updated a model 5 months ago

yuxiaoyang/opsd-llama31-8b-instruct-origin-gen1024-step200-jsdclip006-20260515

Updated May 26 • 7