TreePO: Bridging the Gap of Policy Optimization and Efficacy and Inference Efficiency with Heuristic Tree-based Modeling
Paper
•
2508.17445
•
Published
•
80
TreePO
-
-
m-a-p/TreePO-Qwen2.5-7B
Text Generation • 8B • Updated • 57 • 2 -
m-a-p/TreePO_data
Viewer • Updated • 3.12k • 81 -
m-a-p/TreePO-Qwen2.5-7B_fixed-div
8B • Updated • 55 -
m-a-p/TreePO-Qwen2.5-7B_GRPO-TreePO-Sampling
8B • Updated • 50 -
m-a-p/TreePO-Qwen2.5-7B_Low_Prob_Encourage
8B • Updated • 45 -
m-a-p/TreePO-Qwen2.5-7B_Naive2Low_Scheduler
8B • Updated • 51