cepo-rlvr-self-distillation-using-contrastive-evidence-policy-optimization
wiki · · 1 min read
CEPO: RLVR Self-Distillation using Contrastive Evidence Policy Optimization
Definition
arXiv ID: 2605.19436
Sources
- raw/AI/hf-paper-260519436-CEPO-RLVR-Self-Distillation-using-Contra.md