TreePO: Bridging the Gap of Policy Optimization and Efficacy and Inference Efficiency with Heuristic Tree-based Modeling
Paper • 2508.17445 • Published • 80
train
-
-
agentscope-ai/QwenPaw-Flash-9B
9B • Updated • 368 • 60 -
kai-os/gemma4-31b-Opus-4.6-reasoning
Text Generation • Updated • 9 • 163 -
samuelcardillo/Qwen3-Coder-Next-Opus-4.6-Reasoning-Distilled
6.21M • Updated • 22 • 11 -
HauhauCS/Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive
Image-Text-to-Text • 35B • Updated • 155k • 1.43k -
tanaos/tanaos-text-anonymizer-v1
Token Classification • 0.1B • Updated • 18 • 127 -
sapientinc/HRM-Text-1B
Text Generation • 1B • Updated • 125k • 762 -
openai/privacy-filter
Token Classification • 1B • Updated • 206k • • 1.64k -
microsoft/Phi-4-mini-instruct
Text Generation • 4B • Updated • 983k • • 765 -
nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4
Text Generation • 335B • Updated • 178k • • 174 -
Jackrong/Qwopus3.6-27B-v2-MTP-GGUF
Image-Text-to-Text • Updated • 168k • 294 -
huihui-ai/Huihui-gemma-4-31B-it-qat-q4_0-unquantized-abliterated
Any-to-Any • 33B • Updated • 163 • 12