Rethinking Training-Inference Mismatch in LLM Reinforcement Learning: Where It Arises and How to Correct It
Paper • 2609.32444 • Published • 12
Ben Calvert
bencalvert04
AI & ML interests
Building evals for agents
Recent Activity
upvoted a paper about 11 hours ago
Rethinking Training-Inference Mismatch in LLM Reinforcement Learning: Where It Arises and How to Correct It upvoted a paper 11 days ago
When EOS Tokens Disagree: Understanding Length Inflation in On-Policy Distillation new activity 3 months ago
harborframework/parity-experiments:Add parity experiments for programbenchOrganizations
None yet
upvoted a paper about 11 hours ago
upvoted a paper 11 days ago
Add parity experiments for programbench
#262 opened 3 months ago
by bencalvert04
liked a
dataset 3 months ago