Notabletraining methods

Preference-Based Self-Distillation: Beyond KL Matching via Reward Regularization

arXiv:2605.05040Papers with Code →

Xin Yu, Liuchen Liao, Yiwen Zhang, Yingchen Yu, Lingzhou Xue, Qinzhen Guo

Published
May 6, 2026 — 15:31 UTC
Turing Wire

By Callan Zhang · May 6, 2026 · Editorial standards →

Summarised from the primary source with AI assistance under human editorial oversight. Turing Wire is not a primary source — read the original for the authoritative account.

Source: arXiv cs.AI