Token Utility for On-Policy Distillation via Local Trust-Region Optimization
arXiv 2610.18883v1•33bbbfba758342dc800370fbf21089efab0f30e00e2cf1b9e0e51e02c60fa5fc
Paper metadata
- arXiv ID
- 2610.18883
- Version
- v1
- Category
- cs.AI, cs.LG
- Authors
- Narayanan Sadagopan, Yilan Chen, Vijay Lingam
- Publication date
- 2026-10-15T04:00:00Z
- Source identifier
- 2610.18883v1
- Public record ID
- record:sha256:33bbbfba758342dc800370fbf21089efab0f30e00e2cf1b9e0e51e02c60fa5fc
The PDF link points to arxiv.org. Baitaphish does not expose a private stored PDF.
This is source-provided metadata, not an enriched summary or an impact assessment. Follow the canonical source link for the published material.
Evidence and limitations
- Source ID
- arxiv_research
- Record identifier
- 33bbbfba758342dc800370fbf21089efab0f30e00e2cf1b9e0e51e02c60fa5fc
- Record type
- Source metadata
This record may overlap with other records. Source metadata can be incomplete or change. Validate consequential decisions against the linked source and your own environment.