arXiv CS
open access
Training-Free On-Policy Distillation
On-policy distillation consolidates specialist models into one student at the price of rollouts, teacher passes and gradient steps for every teacher. We show that the consolidation does not need training: with forward passes only, the capabilities of separately tuned specialists can be aggregated in
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
- Training-Free On-Policy Distillation#1357891
- DiffGate: Difficulty-Gated Teacher Guidance for On-Policy Distillation#1200247
- Distill What You Trust: Reliability-Aware Multi-Teacher On-Policy Distillation#1049433
- SAKI: Maximal-Coupling-Routed Teacher Supervision for On-Policy Distillation#1131802
- Compatibility Matters: A Framework for Token-Level Teacher Selection in On-Policy Distillation#1356570
Record · ID 1348851
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