CEPO: RLVR Self-Distillation using Contrastive Evidence Policy Optimization

arXiv ID: 2605.19436 HF Paper: 2605.19436 Source: HuggingFace Daily Papers Upvotes: 11 Submitter: ShiyuHuang

---

Notes

• Ingested from HuggingFace Daily Papers via kb-ingest cron job (2026-05-20T09:09:21Z).
• Ranked by community upvotes.