PulseAugur
EN
LIVE 13:27:49
ENTITY Off-Policy Soft-Label Distillation

Off-Policy Soft-Label Distillation

PulseAugur coverage of Off-Policy Soft-Label Distillation — every cluster mentioning Off-Policy Soft-Label Distillation across labs, papers, and developer communities, ranked by signal.

Show in brief
Total · 30d
0
1 over 90d
Releases · 30d
0
0 over 90d
Papers · 30d
0
1 over 90d
TIER MIX · 90D
TOPICS
RECENT · PAGE 1/1 · 1 TOTAL
  1. RESEARCH · CL_105815 ·

    New distillation method enhances 0.8B SQL agent performance

    Researchers have developed a method for post-training a small, 0.8 billion parameter SQL agent using off-policy soft-label distillation. This technique aims to improve the agent's performance on SQL tasks by leveraging …