arXiv (All)
open access
Not Every Token Is Worth Distilling: Selective Supervision for Direct-OPD
Direct On-Policy Distillation (Direct-OPD) transfers reinforcement-learning-induced policy improvements from a small model to a larger student by using the token-level log-ratio between post-RL and pre-RL checkpoints as dense supervision on the student's own rollouts. This transfer rewards the polic
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
- Is Better Teacher Supervision Enough? Unlocking Student-side Learning in Multimodal On-Policy Distillation#1144087
- Beyond Token Alignment: Event Completion for Cross-Tokenizer On-Policy Distillation#1128996
- Dr. OPD: Learning What to Follow for Optimal On-Policy Distillation of Large Language Models#1142326
- Dr. OPD: Learning What to Follow for Optimal On-Policy Distillation of Large Language Models#1122302
- DASH-OPD: Discrepancy-Aware Switching with Hysteresis for On-Policy Distillation#1070478
Record · ID 1077071
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