arXiv (All)
open access
TISD: On-Policy Self-Distillation with Trajectory Intervention
On-policy self-distillation (OPSD) provides dense teacher targets, but evaluates them only along student-sampled rollouts. When the privileged teacher favors an alternative action at a visited prefix, OPSD can provide a target for the branch decision but cannot supervise the successor contexts induc
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
- OVD: On-policy Verbal Distillation#1128551
- Dense Is Not Enough: Hierarchical Supervision Allocation for Long-Horizon On-Policy Distillation#1118121
- When and Where to Trust the Teacher: Unifying On-Policy Distillation and GRPO through Entropy-Calibrated Credit Assignment#1064988
- An RL View of OPD: Least Square Policy Distillation for Sample-Efficient LLM Reasoning#1130086
- Beam Search as Test-Time Self-Distillation via Counterfactual Contexts#1132242
Record · ID 1105437
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