SampleMix: A Sample-wise Pre-training Data Mixing Strategey by Coordinating Data Quality and Diversity Paper • 2503.01506 • Published Mar 3 • 10
Rethinking Expert Trajectory Utilization in LLM Post-training Paper • 2512.11470 • Published 17 days ago • 7
RETU Collection The official Repository of RETU: Rethinking Expert Trajectory Utilization in LLM Post-training • 9 items • Updated 13 days ago
Rethinking Expert Trajectory Utilization in LLM Post-training Paper • 2512.11470 • Published 17 days ago • 7
RETU Collection The official Repository of RETU: Rethinking Expert Trajectory Utilization in LLM Post-training • 9 items • Updated 13 days ago