arXiv (All)
open access
LastOPD: Taming Collapse in Latent On-Policy Distillation
On-policy distillation (OPD) corrects a student on the responses it writes, but its signal is the teacher's next-token distribution: it tells the student what the teacher says but misses how it thinks. Latent supervision promises the missing part by aligning the student's latent states to the teache
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
- Teacher Should Think Ahead: Adaptive Continuations for Reliable On-Policy Distillation#1036937
- OVD: On-policy Verbal Distillation#1128551
- Beyond Token Alignment: Event Completion for Cross-Tokenizer On-Policy Distillation#1128996
- Graph-Conditioned On-Policy Agent Distillation from Off-the-Shelf Teachers#1141843
- Not Every Token Is Worth Distilling: Selective Supervision for Direct-OPD#1077071
Record · ID 1076501
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