arXiv (All)
open access
Look Before You Select: Rethinking Vocabulary Sparsification in On-Policy Distillation
On-policy distillation (OPD) uses teacher correction on student-generated responses. Full-vocabulary correction can provide important corrections even for tokens that the student assigns low probability, but backpropagating through all token logits becomes memory-intensive for long sequences. Existi
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
- Not Every Token Is Worth Distilling: Selective Supervision for Direct-OPD#1077071
- Calibrating Teacher--Student Discrepancy for On-Policy Distillation#1036015
- Calibrating Teacher--Student Discrepancy for On-Policy Distillation#1006914
- Recursive Self-Improvement via On-Policy Distillation for Reasoning#1105211
- ReTaCo: Residual-Target Control for On-Policy Distillation#1144242
Record · ID 1128658
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