DN-MOPD - a XINLI1997 Collection

XINLI1997 's Collections

WirelessMathBench-XL

DN-MOPD

updated about 12 hours ago

Beyond Teacher Assignment: Domain-Normalized Multi-Teacher On-Policy Distillation. Data and models.

XINLI1997/DN-MOPD-Data

Viewer • Updated about 12 hours ago • 26.7k • 56

Note Training prompt sets: student (2,700) and GRPO teachers (math/code/IF, 8,000 each)
Beyond Teacher Assignment: Domain-Normalized Multi-Teacher On-Policy Distillation

Paper • 2609.35347 • Published 2 days ago • 138

Note Beyond Teacher Assignment: Domain-Normalized Multi-Teacher On-Policy Distillation