arXiv 2609.36601 · cs.AI · 2026-09-29
SAKI: Maximal-Coupling-Routed Teacher Supervision for On-Policy Distillation
Miteto Wei, Xiaohan Wang, Zehao Chen, Jiajun Chai, Sichao Liu, Li Wang, Haoyuan Xu, Zhaoyu Hu and 2 more
meituan
In latest · #163 Added on 2026-10-21
One-line takeaway
SAKI routes distillation supervision using KL-constrained teacher-guided rollouts and maximal coupling to help weak students.
SAKI 用 KL 约束的教师引导采样和最大耦合来分配蒸馏监督，帮助弱学生模型学习。
Read on arXiv PDF Hugging Face discussion Code
Topics & disciplines
More on Efficient training & inference
- The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation ▲511
- Scaling Properties of Same-Family On-Policy Distillation ▲327
- Beyond Domain-Routed Supervision: Cross-Teacher Guarding for Multi-Teacher On-Policy Distillation ▲251
- On-Policy or Off-Policy Learning? A Systematic Study of Distillation Dynamics ▲205
- Beyond Teacher Assignment: Domain-Normalized Multi-Teacher On-Policy Distillation ▲181
About this data
Metadata from the arXiv API (verified); upvotes from Hugging Face Daily Papers; citations from Semantic Scholar. Last refreshed 2026-10-22.
The takeaway is written by AIMap from the abstract; the abstract itself is not reproduced — read the original.