Daniel21Ding/RL62K
Viewer
•
Updated
•
62.3k
•
6
RETU
The official Repository of RETU: Rethinking Expert Trajectory Utilization in LLM Post-training
-
-
Daniel21Ding/uniform102K
Viewer • Updated • 102k • 9 -
Daniel21Ding/Hard102K
Viewer • Updated • 102k • 4 -
Daniel21Ding/Easy102K
Viewer • Updated • 102k • 4 -
Daniel21Ding/SFT889K
Viewer • Updated • 901k • 6 -
Daniel21Ding/S1K_1.1
Viewer • Updated • 1k • 6 -
Daniel21Ding/MIX37K
Viewer • Updated • 36.7k • 7 -
Daniel21Ding/benchmark
Viewer • Updated • 2.91k • 7 -
Rethinking Expert Trajectory Utilization in LLM Post-training
Paper • 2512.11470 • Published • 7