arXiv (All)
open access
The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation
On-policy distillation (OPD) trains a student to match the teacher's next-token distributions on the student's own trajectories and has yielded substantial empirical gains. Generalized variants allow the student to surpass the teacher by extrapolating an implicit reward in output space. The language
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
- Beyond Token Alignment: Event Completion for Cross-Tokenizer On-Policy Distillation#1128996
- When Teacher Guidance Misleads: Reward-Aligned On-Policy Distillation#784737
- When Teacher Guidance Misleads: Reward-Aligned On-Policy Distillation#783147
- Graph-Conditioned On-Policy Agent Distillation from Off-the-Shelf Teachers#1141843
- Leaky Students: Membership Inference against On-Policy Distillation#1117848
Record · ID 1131326
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