-
starriver030515/hapo_data
Viewer • Updated • 1.59k • 17 -
starriver030515/Qwen2.5-Math-1.5B-16k
Text Generation • 2B • Updated • 5 -
starriver030515/Qwen2.5-Math-7B-32k
Text Generation • 8B • Updated • 6 -
From Uniform to Heterogeneous: Tailoring Policy Optimization to Every Token's Nature
Paper • 2509.16591 • Published • 2
Zheng Liu
starriver030515
AI & ML interests
None yet
Organizations
-
starriver030515/hapo_data
Viewer • Updated • 1.59k • 17 -
starriver030515/Qwen2.5-Math-1.5B-16k
Text Generation • 2B • Updated • 5 -
starriver030515/Qwen2.5-Math-7B-32k
Text Generation • 8B • Updated • 6 -
From Uniform to Heterogeneous: Tailoring Policy Optimization to Every Token's Nature
Paper • 2509.16591 • Published • 2
models 38
starriver030515/Qwen2.5-Math-7B-32k
Text Generation • 8B • Updated • 6
starriver030515/Qwen2.5-Math-1.5B-16k
Text Generation • 2B • Updated • 5
starriver030515/sdkfndjgbv
1B • Updated
starriver030515/FUSION-X-Phi3.5-3B
Image-Text-to-Text • 6B • Updated • 19 • 2
starriver030515/FUSION-Phi3.5-3B
Image-Text-to-Text • 5B • Updated • 6
starriver030515/FUSION-X-LLaMA3.1-8B
Image-Text-to-Text • 11B • Updated • 5
starriver030515/FUSION-LLaMA3.1-8B
Image-Text-to-Text • 10B • Updated • 3
starriver030515/FUSION-Phi3.5-3B-Stage1
5B • Updated • 3
starriver030515/FUSION-X-Phi3.5-3B-Stage1
6B • Updated • 3
starriver030515/FUSION-X-LLaMA3.1-8B-Stage1
11B • Updated • 3
datasets 14
starriver030515/chartverse-all
Viewer • Updated • 2.49M • 51
starriver030515/hapo_data
Viewer • Updated • 1.59k • 17
starriver030515/FUSION-Finetune-12M
Viewer • Updated • 1.4k • 3.15k • 13
starriver030515/ocr_eval
Updated • 10
starriver030515/FUSION-Pretrain-10M
Viewer • Updated • 450 • 626 • 9
starriver030515/FUSION-Eval
Updated • 10
starriver030515/FUSION-Synth-4M
Updated • 11
starriver030515/synth_data
Updated • 495
starriver030515/submit
Viewer • Updated • 50.6k • 18
starriver030515/LLaVA_all
Updated • 247