shipfeedAI news, curated daily

23:04:28 CET
20 MAY23:04:28shipfeed⋯
pull to refreshlast sync
Just in — 30 new
§ feed · storyline

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

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

May 6 · · primary fetch1 sourceupdated May 6 ·

This storyline groups 1 article from 1 source. The originating feed didn’t ship an excerpt — open any link below to read the piece.

read full article on arxiv.org ↗
§ sources1 publication · timeline below
  1. arxiv.orgPreference-Based Self-Distillation: Beyond KL Matching via Reward Regularizationprimary
Preference-Based Self-Distillation: Beyond KL Matching via Reward Regularization · shipfeed