Rethinking Training-Inference Mismatch in LLM Reinforcement Learning: Where It Arises and How to Correct It
Paper • 2609.32444 • Published • 8
Zhenyu Wang
Asen9418
AI & ML interests
None yet
Recent Activity
upvoted a paper about 4 hours ago
Rethinking Training-Inference Mismatch in LLM Reinforcement Learning: Where It Arises and How to Correct It upvoted a paper 10 days ago
When EOS Tokens Disagree: Understanding Length Inflation in On-Policy DistillationOrganizations
None yet
upvoted a paper about 4 hours ago