arXiv (All)
open access
CompassOPD: Cross-Family On-Policy Distillation via Within-Family Likelihood Shifts
On-policy distillation (OPD) provides dense token-level supervision on student-generated trajectories. Although OPD performs strongly when teacher and student belong to the same model family, we find that its effectiveness degrades in cross-family settings even after tokenizer alignment, with substa
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
- Beyond Token Alignment: Event Completion for Cross-Tokenizer On-Policy Distillation#1128996
- Dense Is Not Enough: Hierarchical Supervision Allocation for Long-Horizon On-Policy Distillation#1118121
- From Static to Dynamic: On-Policy Distillation from Image to Video Diffusion Models#1128644
- Lightning OPD: Efficient Post-Training for Large Reasoning Models with Offline On-Policy Distillation#1116249
- Teacher-Student Gaps Are Not Enough: Outcome-Guided On-Policy Distillation for Multi-Turn Autonomous Agents#1129911
Record · ID 997065
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