Daniel21Ding/RL62K
Viewer • Updated • 62.3k • 26
RETU
The official Repository of RETU: Rethinking Expert Trajectory Utilization in LLM Post-training
-
-
Daniel21Ding/uniform102K
Viewer • Updated • 102k • 20 -
Daniel21Ding/Hard102K
Viewer • Updated • 102k • 9 -
Daniel21Ding/Easy102K
Viewer • Updated • 102k • 9 -
Daniel21Ding/SFT889K
Viewer • Updated • 901k • 17 -
Daniel21Ding/S1K_1.1
Viewer • Updated • 1k • 6 -
Daniel21Ding/MIX37K
Viewer • Updated • 36.7k • 20 -
Daniel21Ding/benchmark
Viewer • Updated • 2.91k • 15 -
Rethinking Expert Trajectory Utilization in LLM Post-training
Paper • 2512.11470 • Published • 10