arXiv (All)
open access
Spend Teacher Tokens Where They Matter: Success-Referenced On-Policy Distillation
On-policy distillation (OPD) combines student-generated rollouts with dense token-level supervision from a teacher, but providing such supervision for every rollout requires substantial teacher computation. We introduce Success-Referenced On-Policy Distillation (SR-OPD), which reduces this cost by s
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- How Should Teachers Be Prepared? RL on Student-Induced States for On-Policy Distillation#1200601
- Is Better Teacher Supervision Enough? Unlocking Student-side Learning in Multimodal On-Policy Distillation#1144087
- Not Every Token Is Worth Distilling: Selective Supervision for Direct-OPD#1077071
- DASH-OPD: Discrepancy-Aware Switching with Hysteresis for On-Policy Distillation#1070478
- DTDD: Divergence-Triggered Dynamic Distillation for Reliable On-Policy Supervision#1345125
Record · ID 1186992
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive