arXiv (All)
open access
CAST: Credit Alignment for Cross-Tokenizer On-Policy Distillation
Cross-tokenizer on-policy distillation (OPD) requires aligning teacher and student sequences before their scores can be compared. Decoded-text alignment provides such correspondence at the chunk level, but leaves a distinct problem unresolved: credit alignment. A chunk-level signal specifies how muc
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
- What Shared Prefixes Hide: Trajectory Dropout for On-Policy Distillation#1319184
- What Shared Prefixes Hide: Trajectory Dropout for On-Policy Distillation#1118167
- PaDoc: Layout-Grounded Parallel Decoding for Document Parsing#432581
- The Row Normalization Puzzle in Muon#1144081
- Standing on the Shoulders of Giants: Stabilized Knowledge Distillation for Cross--Language Code Clone Detection#155381
Record · ID 1297609
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