Signals 4 · free daily AI digest

OC-OPD: Observation-coordinated Supervision for On-Policy Distillation

Paper recorded by Signals 4 on 2026-11-01 in cs.LG. Abstract reproduced from arXiv; link to the original below.

Published 2026-11-01 on arXiv · recorded by Signals 4 on 2026-11-03

Category: cs.LG · 机器学习 · first seen 2026-11-03

Abstract

Reverse and forward Kullback--Leibler (KL) divergences provide complementary supervision in on-policy distillation: reverse KL refines the student's active token rankings, and forward KL allocates mass to teacher-supported candidates. At student-generated prefixes, we form a four-observation matrix by treating the student and teacher as both candidate sources and evaluators. The diagonal self-obse

Read on arXiv →

#32 most recent of 703 cs.LG papers we have recorded · ↑ newer: Large-Scale Bayesian Optimisation Using Uncertainty-Calibrated Product · ↓ older: Direct Knowledge Transfer for Offline Q-Learning

Cite this page: OC-OPD: Observation-coordinated Supervision for On-Policy Distillation: the #32 most recent of 703 cs.LG papers we have recorded (as of 2026-11-01). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/oc-opd-observation-coordinated-supervision-for-on-policy-distillation.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json

Related: More cs.LG papers · arXiv signals · All papers · Today in AI

Get 4 AI signals a day by email — free.

Subscribe free → See all plans →

Get 4 AI signals a day by email — free

All models · All repos · By company · Daily editions