Paper

OPRD: On-Policy Representation Distillation

arXiv:2606.06021v1 Announce Type: new Abstract: On-policy distillation (OPD) supervises the student only in output space by matching next-token probabilities. This output-only paradigm has two limits: (1) sampling variance from Monte Carlo KL estimates over large vocabularies (e.g., Qwen's ~150k tokens) persists throughout training, and (2) it treats the teacher as a black-box, discarding all intermediate hidden states after the LM head. We propose On-Policy Representation Distillation (OPRD), which lifts distillation into hidden-state space by aligning student and teacher representations acr…

arXiv cs.LGPublished 2026-06-05Paper link

Authors:

Topics

Relevant entities

People

Linked people will appear here.

Related coverage

Linked coverage will appear here.

Related events

Linked events will appear here.

Related discussions

Related discussion nodes will appear here.